Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 27549
    Prev
    Next
    INDEX
    Explanations

    removal processes, "de-" prefix

    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
    Justin
    -0.08
     Zen
    -0.07
    칠
    -0.07
    posed
    -0.07
    𝑠
    -0.07
    _page
    -0.07
    佟
    -0.07
    تين
    -0.06
    衡阳
    -0.06
    案
    -0.06
    POSITIVE LOGITS
    umbing
    0.08
    ݥ
    0.08
    汩
    0.08
    دراس
    0.08
     görüşme
    0.07
     Украины
    0.07
     ActionController
    0.07
    挲
    0.07
     sweaty
    0.07
    制订
    0.07
    Activations Density 0.091%

    No Known Activations