© 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. 68782
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    ưới
    -0.07
     ucwords
    -0.07
    简化
    -0.07
    dle
    -0.07
     introducing
    -0.06
    供给侧
    -0.06
     بتاريخ
    -0.06
    نقص
    -0.06
    izzato
    -0.06
    툽
    -0.06
    POSITIVE LOGITS
    极大的
    0.07
    /per
    0.07
    _detected
    0.07
     Brom
    0.07
     Katrina
    0.07
    更加
    0.07
     Installed
    0.07
    Ren
    0.07
    _Menu
    0.06
     Moved
    0.06
    Activations Density 0.004%

    No Known Activations