© 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. 43795
    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
    IPA
    -0.27
    inate
    -0.26
    ilege
    -0.25
    erdale
    -0.25
    ci
    -0.25
    irate
    -0.24
    pliance
    -0.24
    manent
    -0.24
    ivate
    -0.24
     Isa
    -0.24
    POSITIVE LOGITS
    åıĮèħ¿
    0.30
    ä¸İæŶ
    0.28
    åħ¶æīĢ
    0.26
    æľīè¿Ļæł·çļĦ
    0.26
     suppress
    0.25
    ä¸įæİĴéĻ¤
    0.25
    egend
    0.25
    vers
    0.25
    æľĢ容æĺĵ
    0.24
     Suppress
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.