© 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. 29930
    Prev
    Next
    INDEX
    Explanations

    Scientific citations

    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
    cxx
    -0.32
    èĭĶ
    -0.30
    åĽĽåŃ£
    -0.29
    æĵ¦
    -0.25
    åŃ£èĬĤ
    -0.25
    樱
    -0.24
    åľ¨åĵª
    -0.24
     unidad
    -0.24
    è¿Ļæł·è¯´
    -0.23
    æĥĬå¥ĩ
    -0.23
    POSITIVE LOGITS
    nova
    0.30
    nov
    0.29
     Const
    0.26
    xAE
    0.26
     Thi
    0.25
    ÑĢова
    0.25
    teness
    0.24
     soph
    0.24
    stry
    0.24
    fair
    0.24
    Activations Density 0.613%

    No Known Activations