© 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. 75843
    Prev
    Next
    INDEX
    Explanations

    software licenses/copyright notices

    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
     capped
    -0.08
     çocuklar
    -0.08
    colo
    -0.07
    鲻
    -0.07
    マン
    -0.07
    cono
    -0.07
    ouser
    -0.07
    욝
    -0.07
    达成
    -0.07
    霸
    -0.07
    POSITIVE LOGITS
     reinforcing
    0.07
     <=>
    0.07
    	arg
    0.07
     teachings
    0.07
    )did
    0.07
    铁
    0.07
    (schedule
    0.07
    开心
    0.07
    ()->
    0.07
    哀
    0.06
    Activations Density 0.010%

    No Known Activations