© 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. 22-TRANSCODER-HP
    7. 87876
    Prev
    Next
    INDEX
    Explanations

    Actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çī¹åĪ«å£°æĺİ
    -0.27
    让æĪij们
    -0.26
     Goldberg
    -0.26
    gens
    -0.25
     nos
    -0.24
    è¯Ħæ¯Ķ
    -0.24
    åı¬éĽĨ
    -0.24
    çIJĨ念
    -0.23
     ****************************************************************************
    -0.23
    ContentView
    -0.23
    POSITIVE LOGITS
     Fayette
    0.27
    è§ļ
    0.26
    pla
    0.25
    ĵĺ
    0.25
    least
    0.24
    anzeigen
    0.24
    riet
    0.24
     beat
    0.24
    [".
    0.24
    anything
    0.23
    Activations Density 0.041%

    No Known Activations