© 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. 150287
    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
    verages
    -0.26
    ô
    -0.25
    depend
    -0.25
    èĮ«èĮ«
    -0.24
     Pey
    -0.24
    eos
    -0.24
     mastered
    -0.24
     HD
    -0.24
    ç»ıå¼Ģ
    -0.24
    ä¸įå°ij人
    -0.24
    POSITIVE LOGITS
     геÑĢ
    0.28
     Dmit
    0.27
    .web
    0.26
    æĹ¶ä»£
    0.25
     Sparks
    0.25
    _SIMPLE
    0.24
    ICA
    0.24
    Interaction
    0.23
    ,proto
    0.23
    INO
    0.23
    Activations Density 2.401%

    No Known Activations

    This feature has no known activations.