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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 19-RESID-POST-AA
    6. 88164
    Prev
    Next
    INDEX
    Explanations

    scientific and technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    有所帮助
    -0.08
    埫
    -0.07
    (nd
    -0.07
    したもの
    -0.06
    🖑
    -0.06
    情况来看
    -0.06
    \Order
    -0.06
    Ⓟ
    -0.06
    emsp
    -0.06
     damaged
    -0.06
    POSITIVE LOGITS
     diret
    0.07
    剑
    0.07
    recur
    0.07
    arel
    0.07
    退出
    0.07
     harass
    0.07
    ThreadId
    0.07
    强制
    0.07
     Romero
    0.07
    .itemView
    0.07
    Activations Density 0.168%

    No Known Activations