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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 109838
    Prev
    Next
    INDEX
    Explanations

    )^

    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
    쳥
    -0.07
     centre
    -0.07
     protection
    -0.07
    pst
    -0.06
    нятие
    -0.06
    ♤
    -0.06
    用手
    -0.06
    耒
    -0.06
    >F
    -0.06
    פלסט
    -0.06
    POSITIVE LOGITS
    .Verify
    0.07
     álbum
    0.07
    是不可能
    0.07
    (This
    0.07
    围绕
    0.07
    .getVersion
    0.07
     comfortable
    0.07
     leads
    0.07
    ='../
    0.07
     viable
    0.07
    Activations Density 0.031%

    No Known Activations