© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 14501
    Prev
    Next
    INDEX
    Explanations

    Code/technical documents

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritch
    -0.07
    身穿
    -0.07
    ва
    -0.06
    almö
    -0.06
     readFile
    -0.06
     rk
    -0.06
     tokenId
    -0.06
    äs
    -0.06
    付き合
    -0.06
    ondrous
    -0.06
    POSITIVE LOGITS
     election
    0.07
    -road
    0.07
    /left
    0.07
    optic
    0.07
    _subject
    0.07
    驳
    0.06
     Presents
    0.06
    .Edit
    0.06
    depend
    0.06
    圉
    0.06
    Activations Density 0.061%

    No Known Activations