© 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. 27-TRANSCODER-HP
    7. 8655
    Prev
    Next
    INDEX
    Explanations

    Technical/programming context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urve
    -0.30
     afterwards
    -0.26
    ihar
    -0.25
    ulkan
    -0.24
    çļĦæł·åŃIJ
    -0.24
    çļĦèīºæľ¯
    -0.24
    uptools
    -0.24
    SURE
    -0.24
    ÙĤØ©
    -0.23
    ulas
    -0.23
    POSITIVE LOGITS
     onto
    0.29
    åħ¬çĽĬæĢ§
    0.28
    åĿIJåľ¨
    0.28
    éļĶçĿĢ
    0.27
    éĥ½è¢«
    0.27
    ç½ijç«Ļåľ°åĽ¾
    0.26
    onto
    0.26
    æĪIJ交
    0.26
    èººåľ¨
    0.25
    è£Ķ
    0.24
    Activations Density 0.010%

    No Known Activations