© 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. 32-TRANSCODER-HP
    7. 42379
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accomplished
    -0.26
    tol
    -0.26
    /tty
    -0.25
     dec
    -0.25
     de
    -0.25
    tar
    -0.24
    isp
    -0.24
    -Oct
    -0.24
     outcome
    -0.24
     stamp
    -0.24
    POSITIVE LOGITS
     Holmes
    0.28
    æĽ´æľī
    0.26
    IID
    0.26
     cof
    0.26
    odings
    0.26
     szer
    0.25
    Structured
    0.25
    rnd
    0.25
    лан
    0.25
     trá»Ŀi
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.