© 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. 43408
    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
    ilage
    -0.27
    梦
    -0.26
    .tie
    -0.25
    å¼ĢåıijèĢħ
    -0.25
    ETERS
    -0.24
    æ±IJ
    -0.24
    facility
    -0.24
     ignor
    -0.24
     surveys
    -0.23
     quicker
    -0.23
    POSITIVE LOGITS
    å¹³åĿ¦
    0.31
    .INSTANCE
    0.29
    åģĥ
    0.27
    getClass
    0.26
    /examples
    0.25
    姿æĢģ
    0.24
    糧
    0.24
    æѤ类
    0.24
    ccess
    0.24
    æŃ¤æ¬¡
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.