© 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. 30-TRANSCODER-HP
    7. 96377
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rightness
    -0.26
    ughter
    -0.26
    zm
    -0.26
    lesia
    -0.25
    irected
    -0.25
     hữu
    -0.25
    ughters
    -0.25
    ENTS
    -0.24
    ropri
    -0.24
    ughs
    -0.24
    POSITIVE LOGITS
     dif
    0.28
    ¢åįķ
    0.27
    _bucket
    0.26
    åĪĨåĮĸ
    0.26
    没æľī
    0.26
    åºĵ
    0.25
     Buck
    0.25
    authorized
    0.24
     bucket
    0.24
    å¥Ĺ
    0.24
    Activations Density 2.306%

    No Known Activations

    This feature has no known activations.