© 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. 20-TRANSCODER-HP
    7. 140947
    Prev
    Next
    INDEX
    Explanations

    voice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icals
    -0.28
    ercul
    -0.27
    社群
    -0.26
     íķŃ
    -0.26
    ijk
    -0.26
    tl
    -0.25
     pok
    -0.25
    TOP
    -0.25
    antz
    -0.24
    erc
    -0.24
    POSITIVE LOGITS
     alphabet
    0.27
    éķ¿éķ¿çļĦ
    0.26
    leys
    0.25
    车éĺŁ
    0.25
     bitter
    0.25
    éĢģ
    0.25
    mé
    0.24
    mens
    0.24
    mans
    0.24
    æĮŁ
    0.24
    Activations Density 14.626%

    No Known Activations