© 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. 22-TRANSCODER-HP
    7. 87623
    Prev
    Next
    INDEX
    Explanations

    Code/Copyright text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outing
    -0.28
    ----------č↵
    -0.27
    venge
    -0.26
    äºĭä¸ļéĥ¨
    -0.26
    iful
    -0.25
    yre
    -0.25
    伸åĩº
    -0.24
    åĢ¾
    -0.24
    æ¯ħ
    -0.24
    è¾ķ
    -0.23
    POSITIVE LOGITS
    _vect
    0.27
    转身
    0.27
    éģ·
    0.26
    å¾Ĺ天
    0.26
    leine
    0.25
     meltdown
    0.25
    身å¿ĥåģ¥åº·
    0.24
    akov
    0.24
    rep
    0.23
     luck
    0.23
    Activations Density 0.015%

    No Known Activations