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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107390
    Prev
    Next
    INDEX
    Explanations

    assassination

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otropic
    -0.30
    转ä¼ļ
    -0.29
    åľ°åĿª
    -0.29
     tame
    -0.26
    accept
    -0.26
     suscept
    -0.26
     repl
    -0.26
     hor
    -0.25
    IllegalAccessException
    -0.25
     ages
    -0.25
    POSITIVE LOGITS
    æ³¾
    0.29
    _traits
    0.29
    пад
    0.25
    Rect
    0.25
    !=(
    0.24
    çĹ´
    0.24
    TypeId
    0.24
    ä¼Ĭå§ĭ
    0.24
    åİ¢
    0.23
    ÑĢаÐ
    0.23
    Activations Density 1.134%

    No Known Activations