© 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. 24-TRANSCODER-HP
    7. 150675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     afford
    -0.26
    æľªæĪIJ
    -0.26
    åĪĨåī²
    -0.26
    è¿ĩæĿ¥
    -0.26
    产åĩº
    -0.24
     stro
    -0.24
    弧
    -0.24
     ìłijê·¼
    -0.23
     arc
    -0.23
    /INFO
    -0.23
    POSITIVE LOGITS
     naw
    0.25
    .neg
    0.25
    website
    0.25
     NEG
    0.25
    µ¬
    0.24
     +#+
    0.24
    åĮ¾
    0.24
    dojo
    0.23
     República
    0.23
    +-+-
    0.23
    Activations Density 0.894%

    No Known Activations

    This feature has no known activations.