© 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. 23801
    Prev
    Next
    INDEX
    Explanations

    advertisements and offers

    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
    icha
    -0.33
    gef
    -0.28
    ();)
    -0.28
    istar
    -0.28
     addAction
    -0.26
    indexed
    -0.26
    haven
    -0.26
    plers
    -0.26
    heard
    -0.26
     heraus
    -0.25
    POSITIVE LOGITS
     Rosen
    0.26
     DÅ©ng
    0.24
    ìĤ¬ìĿ´
    0.24
    illow
    0.23
    [/
    0.23
    notation
    0.23
    åľ¨æĹ¥æľ¬
    0.23
     Strike
    0.23
     Gentle
    0.23
    è²łãģij
    0.22
    Activations Density 0.006%

    No Known Activations