© 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. 108265
    Prev
    Next
    INDEX
    Explanations

    Technical details

    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
    ä¸Ģç¢Ĺ
    -0.28
    åľ¨åħ¨åĽ½
    -0.27
    å§ĵ
    -0.27
    cord
    -0.26
     lick
    -0.26
    Cookie
    -0.25
    ä¸Ģ大
    -0.25
    closing
    -0.25
    é¼»åŃIJ
    -0.24
    齿
    -0.24
    POSITIVE LOGITS
    icast
    0.29
    :\/\/
    0.26
    onium
    0.24
     trials
    0.24
     squ
    0.23
     Wolff
    0.23
     Trials
    0.23
    urbed
    0.23
     Freem
    0.23
    _put
    0.22
    Activations Density 1.283%

    No Known Activations