© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 89658
    Prev
    Next
    INDEX
    Explanations

    -H

    np_max-act · gemini-2.0-flash

    categorical or structural qualifiers and tags—short all-caps codes, variant suffix letters, and positional/level descriptors indicating location or type distinctions.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olk
    -0.07
     עסקי
    -0.07
     SCN
    -0.07
    تقد
    -0.07
    难怪
    -0.06
    方言
    -0.06
    Unc
    -0.06
    awesome
    -0.06
    أشك
    -0.06
    Sac
    -0.06
    POSITIVE LOGITS
     הז
    0.08
    0.08
    งาน
    0.07
    一个小时
    0.07
    plings
    0.07
    借款
    0.07
    fst
    0.07
    _mr
    0.07
    FIRST
    0.07
    lng
    0.07
    Activations Density 0.175%

    No Known Activations