© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 30161
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ((__
    -0.33
    __[
    -0.29
    æĢİä¹Īåģļ
    -0.29
    å§Ķåijĺä¼ļ
    -0.27
    åģļä»Ģä¹Ī
    -0.26
    quer
    -0.26
     cyclic
    -0.26
    è¯Ħæµĭ
    -0.26
    年度
    -0.26
    uck
    -0.25
    POSITIVE LOGITS
    uled
    0.30
    éĿĸ
    0.27
    agos
    0.27
    ardless
    0.26
    aho
    0.26
    IÃĵN
    0.26
     LED
    0.26
    apo
    0.25
    roduced
    0.24
     fart
    0.24
    Activations Density 6.419%

    No Known Activations