© 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. 35-TRANSCODER-HP
    7. 40513
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    amped
    -0.32
    irma
    -0.31
    aren
    -0.31
    ima
    -0.31
    istan
    -0.30
    ami
    -0.29
    endant
    -0.28
    sam
    -0.28
    amo
    -0.28
    amente
    -0.28
    POSITIVE LOGITS
    ck
    0.40
    cket
    0.38
    cki
    0.35
    oth
    0.34
    tk
    0.34
    tte
    0.33
    cth
    0.32
    ff
    0.31
    cctor
    0.31
    ton
    0.31
    Activations Density 20.430%

    No Known Activations