© 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. 23-TRANSCODER-HP
    7. 24862
    Prev
    Next
    INDEX
    Explanations

    web hosting and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹħè¡Į
    -0.28
     craz
    -0.27
     engineering
    -0.26
     autonomous
    -0.26
    wear
    -0.26
    rama
    -0.25
    çĤ¼
    -0.25
    .reporting
    -0.25
    AtPath
    -0.25
    лÑĭ
    -0.24
    POSITIVE LOGITS
    è¿Ļç¯ĩæĸĩç«ł
    0.27
    neighbor
    0.25
    诬
    0.25
    {}'.
    0.25
    éĻįæ°´
    0.24
     neighborhood
    0.24
    âݨ
    0.24
    amura
    0.24
    -ci
    0.23
    åĮºç®¡å§Ķä¼ļ
    0.23
    Activations Density 0.001%

    No Known Activations