© 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. 23-TRANSCODER-HP
    7. 24566
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĵĦ
    -0.29
    ãĥ¬ãĤ¹ãĥĪ
    -0.25
    è¾ķ
    -0.24
     felt
    -0.24
    ave
    -0.24
    箪
    -0.24
     ve
    -0.24
     rh
    -0.23
    æ·±çŁ¥
    -0.23
     vol
    -0.23
    POSITIVE LOGITS
    ually
    0.32
    igor
    0.25
    mith
    0.25
     наÑĩал
    0.24
    å°ij
    0.24
    æĭ³
    0.24
    鼶
    0.23
    æĸ¹åIJijçĽĺ
    0.23
    plane
    0.23
    å´ĸ
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.