© 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. 129321
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    amic
    -0.31
    ç»´
    -0.28
    eya
    -0.26
    åĵī
    -0.25
    .Caption
    -0.25
    gae
    -0.24
    å§ĭç»Īä¿ĿæĮģ
    -0.24
    amation
    -0.24
    amina
    -0.23
    ptime
    -0.23
    POSITIVE LOGITS
    plies
    0.32
     ch
    0.26
    outil
    0.25
     than
    0.25
     Matters
    0.25
     Fond
    0.24
     اÙĦÙħÙĨت
    0.24
     pare
    0.24
    `s
    0.24
     affected
    0.24
    Activations Density 0.011%

    No Known Activations