© 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. 150752
    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
    Coder
    -0.29
    æĽľ
    -0.27
    ring
    -0.27
    åģľ
    -0.26
     circum
    -0.26
    çķĻä½ı
    -0.26
    çĻ»
    -0.25
    çķĻ
    -0.25
    utex
    -0.25
     mounts
    -0.25
    POSITIVE LOGITS
    getDisplay
    0.28
     Leh
    0.26
    ëĿ¼
    0.26
    prefs
    0.25
    æĹ»
    0.25
    labs
    0.24
     supply
    0.24
    è¿ľç¦»
    0.24
    ä¾Ľç»Ļ
    0.24
    akt
    0.23
    Activations Density 2.946%

    No Known Activations

    This feature has no known activations.