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. 6877
    Prev
    Next
    INDEX
    Explanations

    say "education"

    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
     окружа
    -0.08
     Plum
    -0.08
     Amelia
    -0.07
    ◝
    -0.07
    Luck
    -0.07
     surround
    -0.07
     беременн
    -0.07
     geral
    -0.07
    这么多
    -0.07
    🔉
    -0.07
    POSITIVE LOGITS
    薪资
    0.07
    BASH
    0.07
     notions
    0.07
    _masks
    0.07
    戢
    0.07
    .figure
    0.07
     nichts
    0.07
    :=
    0.07
    Bytes
    0.07
    返乡
    0.07
    Activations Density 0.016%

    No Known Activations