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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RESID-POST-AA
    6. 41432
    Prev
    Next
    INDEX
    Explanations

    CT

    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
    âm
    -0.07
    تراث
    -0.07
    祭
    -0.07
     quoi
    -0.07
    .ID
    -0.07
     EE
    -0.07
     Ticket
    -0.07
     beide
    -0.07
     Weed
    -0.07
     Joomla
    -0.07
    POSITIVE LOGITS
    hots
    0.07
    |
    ↵
    0.07
     ...
    ↵
    0.07
     stał
    0.07
    been
    0.07
    very
    0.07
    Inverse
    0.06
     ","↵
    0.06
    .githubusercontent
    0.06
     ont
    0.06
    Activations Density 0.007%

    No Known Activations