© 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. 76077
    Prev
    Next
    INDEX
    Explanations

    year

    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
     passage
    -0.07
     May
    -0.07
     Weiss
    -0.06
     XI
    -0.06
     Worship
    -0.06
     gloss
    -0.06
     TERMS
    -0.06
    鲁
    -0.06
     Warrior
    -0.06
     tcb
    -0.06
    POSITIVE LOGITS
    🌀
    0.07
     klientów
    0.07
    شب
    0.07
    //---------------------------------------------------------------------------↵↵
    0.07
    actable
    0.07
    -cigarettes
    0.07
    닿
    0.07
     sản
    0.07
    CHandle
    0.07
     코드
    0.07
    Activations Density 0.036%

    No Known Activations