© 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. 84964
    Prev
    Next
    INDEX
    Explanations

    DW

    np_max-act · gemini-2.0-flash
    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
    .ID
    -0.07
     aid
    -0.07
    spy
    -0.07
    필
    -0.07
    ㆍ
    -0.07
     bí
    -0.07
    赖以
    -0.07
    _ant
    -0.07
     ضد
    -0.07
    袤
    -0.06
    POSITIVE LOGITS
     Essentials
    0.07
    ?");↵
    0.07
    ыш
    0.07
     thresholds
    0.06
    Adventure
    0.06
    aket
    0.06
    توا
    0.06
    務
    0.06
    естеств
    0.06
    larınızı
    0.06
    Activations Density 0.001%

    No Known Activations