© 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. 43747
    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
     Ir
    -0.29
     solids
    -0.28
    _Checked
    -0.27
    åĽº
    -0.27
    eme
    -0.27
    å¸Ńåį·
    -0.27
     brand
    -0.26
    blank
    -0.25
     ir
    -0.25
    åħ¬åħ±èµĦæºIJ
    -0.25
    POSITIVE LOGITS
    æ¼ĵ
    0.28
    unix
    0.28
     Subjects
    0.28
    asar
    0.28
    .env
    0.26
    æ©¡
    0.26
    _unix
    0.26
    Detach
    0.26
    对åѦçĶŁ
    0.25
    WC
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.