© 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. 150256
    Prev
    Next
    INDEX
    Explanations

    Borders and boundaries

    np_max-act-logits · gemini-2.0-flash
    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
     Kn
    -0.29
     AppModule
    -0.27
     EventHandler
    -0.26
    synthesize
    -0.26
    earning
    -0.25
     turbulence
    -0.25
    _Db
    -0.24
     warmly
    -0.24
     propTypes
    -0.24
     transporting
    -0.24
    POSITIVE LOGITS
    ä¸¤åĽ½
    0.29
    åĭĺ
    0.28
    æ¶Ī
    0.28
    è¡ĮæĶ¿åĮº
    0.28
    åıĮæĸ¹
    0.27
    æīĺ管
    0.26
    iloc
    0.26
    åIJĪéĢĤçļĦ
    0.26
     mess
    0.26
     border
    0.26
    Activations Density 0.128%

    No Known Activations