© 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. 86015
    Prev
    Next
    INDEX
    Explanations

    Na

    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
    装扮
    -0.08
    ✺
    -0.08
    /respond
    -0.07
     colour
    -0.07
     bass
    -0.07
     Rug
    -0.07
    ereg
    -0.07
     CORE
    -0.07
    眼袋
    -0.07
     Amber
    -0.07
    POSITIVE LOGITS
     quando
    0.07
    遇
    0.07
    젹
    0.07
    /year
    0.07
    劾
    0.07
    na
    0.07
     ciągu
    0.07
     NA
    0.07
     na
    0.06
    将继续
    0.06
    Activations Density 0.025%

    No Known Activations