© 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. 24495
    Prev
    Next
    INDEX
    Explanations

    People and their roles

    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
    ä¸įä¿¡
    -0.25
    orate
    -0.25
     direkt
    -0.24
    æ±Ľ
    -0.24
    çī¹æ®ĬæĥħåĨµ
    -0.24
    port
    -0.24
     NI
    -0.23
    orting
    -0.23
    riminal
    -0.23
    éĢļ
    -0.23
    POSITIVE LOGITS
    ube
    0.28
    ovy
    0.26
    æ£ĺ
    0.26
    okit
    0.25
     Cra
    0.24
    bags
    0.24
    bag
    0.24
    举æŃ¢
    0.24
    ebra
    0.24
     baggage
    0.23
    Activations Density 0.005%

    No Known Activations