© 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. 9-TRANSCODER-HP
    7. 30036
    Prev
    Next
    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç®ĹäºĨ
    -0.25
     tear
    -0.25
    (calc
    -0.25
     ascend
    -0.24
    "))↵↵
    -0.24
    ."));↵
    -0.24
    ана
    -0.24
     μ
    -0.23
    '))↵↵
    -0.23
    ãģ¨åħ±
    -0.23
    POSITIVE LOGITS
    纪å§Ķ书记
    0.29
    çļij
    0.28
     Chall
    0.27
    omy
    0.27
    æ³¼
    0.27
    firstname
    0.26
    GU
    0.26
    ncia
    0.25
    åıĶ
    0.25
    subtitle
    0.25
    Activations Density 4.496%

    No Known Activations