© 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. 23984
    Prev
    Next
    INDEX
    Explanations

    Eric

    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
    universal
    -0.30
    elt
    -0.27
    cascade
    -0.27
    sphere
    -0.26
    duced
    -0.26
    对æĪij
    -0.26
    sources
    -0.26
    s
    -0.26
    pieces
    -0.26
    quila
    -0.26
    POSITIVE LOGITS
     joking
    0.30
    ames
    0.28
    åĦ¿
    0.26
    enko
    0.26
    åħĴ
    0.24
    antly
    0.24
     Vo
    0.23
    ий
    0.23
    ·¨
    0.23
    è¿ĽèĢĮ
    0.22
    Activations Density 0.202%

    No Known Activations