© 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. 112315
    Prev
    Next
    INDEX
    Explanations

    Named entities/proper nouns

    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
    ey
    -0.27
    ège
    -0.26
    ives
    -0.25
    ôi
    -0.25
    istring
    -0.25
    oy
    -0.24
    ROWS
    -0.24
    clair
    -0.24
    ä¸ĢèĦļ
    -0.24
    itori
    -0.23
    POSITIVE LOGITS
    SSI
    0.26
    FY
    0.25
    ONUS
    0.24
    ³³
    0.23
    pNext
    0.22
    èĸªæ°´
    0.22
     ------>
    0.22
     THAN
    0.22
    BST
    0.22
     sponge
    0.22
    Activations Density 0.013%

    No Known Activations