© 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. 150512
    Prev
    Next
    INDEX
    Explanations

    term

    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
    arking
    -0.28
    rary
    -0.27
    æĸĩ
    -0.25
    æºIJ头
    -0.25
    ark
    -0.25
    ipo
    -0.24
    aku
    -0.24
     reproduce
    -0.24
    ZX
    -0.24
    ailles
    -0.24
    POSITIVE LOGITS
     or
    0.30
    æĪĸèĢħæĺ¯
    0.30
    æĪĸæĺ¯
    0.30
    æĪijè¿ĺæĺ¯
    0.27
     ret
    0.26
    è¾ĥé«ĺçļĦ
    0.25
    æĪĸèĢħ
    0.25
     hospitalized
    0.25
     unemployed
    0.25
     RET
    0.24
    Activations Density 0.923%

    No Known Activations