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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 41203
    Prev
    Next
    INDEX
    Explanations

    synchron

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .embed
    -0.07
     por
    -0.07
    ő
    -0.07
    .GetOrdinal
    -0.07
    .f
    -0.06
     dwind
    -0.06
    ingga
    -0.06
     unearth
    -0.06
    DataGridView
    -0.06
    perse
    -0.06
    POSITIVE LOGITS
     safest
    0.08
    얗
    0.07
    Watcher
    0.07
    Подроб
    0.07
     Everything
    0.07
     Meat
    0.06
     Passive
    0.06
    caught
    0.06
     Locate
    0.06
     WARRANTY
    0.06
    Activations Density 0.299%

    No Known Activations