© 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. 150081
    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
     inc
    -0.33
    Inc
    -0.30
     Inc
    -0.29
    ursive
    -0.27
    inc
    -0.27
     plac
    -0.27
    ensor
    -0.27
    angel
    -0.27
     truncate
    -0.26
    ording
    -0.26
    POSITIVE LOGITS
    /bit
    0.28
    ASSES
    0.26
    è£Ĩ
    0.26
    kf
    0.25
    rar
    0.25
    ystone
    0.25
    åĽ´è§Ĥ
    0.25
     baja
    0.24
    涸
    0.24
     performance
    0.24
    Activations Density 1.205%

    No Known Activations

    This feature has no known activations.