© 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. 38752
    Prev
    Next
    INDEX
    Explanations

    words ending in "y"

    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
     intel
    -0.28
    andle
    -0.27
    itere
    -0.26
    ansen
    -0.26
     intern
    -0.25
    æł¼å°Ķ
    -0.24
    CTS
    -0.24
    è±¹
    -0.24
     masc
    -0.23
     consort
    -0.23
    POSITIVE LOGITS
    gy
    0.84
     Dy
    0.83
     dy
    0.83
     gy
    0.82
    dy
    0.81
    Wy
    0.81
     Gy
    0.80
     Wy
    0.80
    ny
    0.79
    vy
    0.79
    Activations Density 72.969%

    No Known Activations