© 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. 128808
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    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
     Pictures
    -0.07
    imet
    -0.07
    买车
    -0.07
     starts
    -0.07
    酮
    -0.07
    енд
    -0.07
    /licenses
    -0.07
    全世界
    -0.07
    .createComponent
    -0.07
     Netherlands
    -0.07
    POSITIVE LOGITS
    原料
    0.07
    Stay
    0.07
    Juan
    0.06
    ga
    0.06
     delegate
    0.06
    .tree
    0.06
     foul
    0.06
     flask
    0.06
    瀱
    0.06
    𬘯
    0.06
    Activations Density 0.030%

    No Known Activations