© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 89425
    Prev
    Next
    INDEX
    Explanations

    interdisciplinary

    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
    投入到
    -0.08
    大叔
    -0.07
     espera
    -0.07
    rt
    -0.07
    renderer
    -0.07
    HOST
    -0.07
     Storage
    -0.07
    旅客
    -0.07
    城镇
    -0.07
    趁
    -0.07
    POSITIVE LOGITS
    ㉣
    0.07
    皛
    0.07
    되면
    0.07
    ergarten
    0.07
    莫名其
    0.07
    这样一来
    0.07
    ffield
    0.07
    杜兰特
    0.07
    🌂
    0.06
    🅰
    0.06
    Activations Density 0.006%

    No Known Activations