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. 71642
    Prev
    Next
    INDEX
    Explanations

    say "Aws" word

    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
    .web
    -0.07
    卫生
    -0.07
    电工
    -0.07
    保温
    -0.07
     trucks
    -0.07
    _TAGS
    -0.07
    "M
    -0.06
     máu
    -0.06
     DEA
    -0.06
    的心情
    -0.06
    POSITIVE LOGITS
    均衡
    0.07
    rz
    0.07
    JsonObject
    0.07
    .Country
    0.06
     reim
    0.06
     marshal
    0.06
    Parent
    0.06
     partners
    0.06
    Changed
    0.06
    七十
    0.06
    Activations Density 0.000%

    No Known Activations