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. 6843
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ожет
    -0.07
    Ơ
    -0.07
    (hdc
    -0.07
    .Dimension
    -0.07
    GORITHM
    -0.07
     quirky
    -0.07
     ROUND
    -0.07
    柴纳
    -0.07
     creamy
    -0.07
    (float
    -0.07
    POSITIVE LOGITS
    .operations
    0.08
     resolved
    0.07
     Caleb
    0.07
     ";
    0.07
    cial
    0.07
    �
    0.06
    ��
    0.06
     posts
    0.06
     omitted
    0.06
    ">&
    0.06
    Activations Density 0.004%

    No Known Activations