© 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. 38598
    Prev
    Next
    INDEX
    Explanations

    say "m" words

    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
     advocating
    -0.26
     invent
    -0.25
     taxp
    -0.24
    olut
    -0.24
    对æĬĹ
    -0.24
    opot
    -0.24
    ota
    -0.24
     capt
    -0.24
     advocacy
    -0.23
    alin
    -0.23
    POSITIVE LOGITS
    m
    0.61
    mA
    0.48
    ï½į
    0.48
    me
    0.45
    mpr
    0.45
    ms
    0.44
    ming
    0.44
    mm
    0.44
    mq
    0.43
    ðĿijļ
    0.42
    Activations Density 1.935%

    No Known Activations