© 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. 29646
    Prev
    Next
    INDEX
    Explanations

    It

    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
    认è¯Ĩ
    -0.27
    èĻ¹
    -0.26
    squ
    -0.26
    ulton
    -0.25
    ĽĦ
    -0.25
    è¿ĻäºĽéĥ½æĺ¯
    -0.25
    侬
    -0.25
    encent
    -0.24
    ogn
    -0.24
    ç»Ĩ
    -0.24
    POSITIVE LOGITS
    aines
    0.32
    Submitting
    0.28
    iasm
    0.27
    _segments
    0.26
    iker
    0.26
    ä¸įåħ¬å¹³
    0.26
    inars
    0.26
    umes
    0.26
    åħ¨åİ¿
    0.26
    ãĢĤwww
    0.25
    Activations Density 0.087%

    No Known Activations