© 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. 15-RESID-POST-AA
    11. 123624
    Prev
    Next
    INDEX
    Explanations

    Endings and duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SMB
    -0.07
    /bind
    -0.07
    _display
    -0.07
     vốn
    -0.07
    _servers
    -0.07
    ﷻ
    -0.07
     meant
    -0.07
    痴迷
    -0.07
    La
    -0.07
    webdriver
    -0.07
    POSITIVE LOGITS
    gy
    0.08
    苓
    0.07
    cio
    0.07
     introdu
    0.07
    便可
    0.07
    떻
    0.06
    篇文章
    0.06
    squ
    0.06
     пов
    0.06
     Hew
    0.06
    Activations Density 0.030%

    No Known Activations