© 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. 9-TRANSCODER-HP
    7. 29754
    Prev
    Next
    INDEX
    Explanations

    variety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     гол
    -0.28
    enders
    -0.26
    ença
    -0.26
    åIJį
    -0.26
    lices
    -0.26
    éŨåı£
    -0.26
    åĽŃ
    -0.26
    è°Ķ
    -0.26
    æľ¬æĽ¸
    -0.25
    illac
    -0.24
    POSITIVE LOGITS
    秣
    0.27
    åľ¨æ·±åľ³
    0.27
     infer
    0.27
    åľ¨å¹¿å·ŀ
    0.26
     Niger
    0.24
     Cos
    0.24
     fr
    0.24
     art
    0.24
    fsp
    0.23
     enumeration
    0.23
    Activations Density 1.555%

    No Known Activations