© 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. 42015
    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
    plib
    -0.28
    ↵                    ↵
    -0.27
    Dig
    -0.26
    pz
    -0.26
     Schwe
    -0.26
     vt
    -0.25
    çļĦ第ä¸Ģ个
    -0.25
    /tos
    -0.25
     tph
    -0.25
    mts
    -0.25
    POSITIVE LOGITS
    è¿ĩäºĨ
    0.27
     imperative
    0.27
    inned
    0.26
    äºĨä¸ĭæĿ¥
    0.25
    flare
    0.25
    ived
    0.25
     room
    0.24
    elled
    0.24
    æŁIJ
    0.24
     marginal
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.