© 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. 70306
    Prev
    Next
    INDEX
    Explanations

    Plagiarism detection

    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
     Nack
    -0.08
    させる
    -0.08
     кру
    -0.07
    🛑
    -0.07
    owards
    -0.07
     Gins
    -0.07
    때
    -0.07
     disarm
    -0.07
    —is
    -0.07
    出来る
    -0.07
    POSITIVE LOGITS
    ։
    0.06
     può
    0.06
    ~-~-
    0.06
    Sub
    0.06
    Prob
    0.06
     EX
    0.06
    Heavy
    0.06
     `
    0.06
    tp
    0.06
    投資
    0.06
    Activations Density 0.003%

    No Known Activations