© 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. 151010
    Prev
    Next
    INDEX
    Explanations

    think

    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
    ä¼ļéĢīæĭ©
    -0.27
    ä½ľåĵģ
    -0.26
    spr
    -0.25
    ä¼ļéķ¿
    -0.25
    åIJ¯
    -0.24
    æݨèįIJéĺħ读
    -0.24
    ä»Ģä¹Īåľ°æĸ¹
    -0.24
    åIJ¯ç¤º
    -0.24
    æ°´çĶµ
    -0.24
    speech
    -0.23
    POSITIVE LOGITS
    DTV
    0.28
     now
    0.27
     ultimately
    0.26
    黳
    0.26
     moreover
    0.26
    ä½ľä¸ºä¸Ģ个
    0.26
     fortunately
    0.25
    åĽłä¸ºæĪij
    0.25
     throughout
    0.25
    .now
    0.25
    Activations Density 0.210%

    No Known Activations