© 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. 19-RESID-POST-AA
    11. 5208
    Prev
    Next
    INDEX
    Explanations

    run

    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
    跐
    -0.07
     Mater
    -0.07
    Aud
    -0.06
    、“
    -0.06
     fiyatı
    -0.06
    Corner
    -0.06
    招股
    -0.06
     bass
    -0.06
     Stamford
    -0.06
     Recreation
    -0.06
    POSITIVE LOGITS
    (net
    0.08
    _hex
    0.07
    (seg
    0.07
     =================
    0.06
    xFA
    0.06
    un
    0.06
     xml
    0.06
     //////////////////
    0.06
     valleys
    0.06
     PH
    0.06
    Activations Density 0.002%

    No Known Activations