© 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. 13437
    Prev
    Next
    INDEX
    Explanations

    electricity, activation

    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
     Dmitry
    -0.07
    掌握
    -0.07
     tournament
    -0.06
     amph
    -0.06
    기도
    -0.06
     הר
    -0.06
    omain
    -0.06
    {lng
    -0.06
     ülkem
    -0.06
     looming
    -0.06
    POSITIVE LOGITS
    greens
    0.08
     đã
    0.07
     wah
    0.06
     JQuery
    0.06
     Atkins
    0.06
     liqu
    0.06
     conclus
    0.06
    uggestion
    0.06
    印花
    0.06
    就是这样
    0.06
    Activations Density 0.069%

    No Known Activations