© 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. 38624
    Prev
    Next
    INDEX
    Explanations

    say "ly"

    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
    azio
    -0.28
    à¹Ģà¸Ĺ
    -0.27
    æīģ
    -0.27
    åĢ¼å¾Ĺ
    -0.26
    mai
    -0.25
    à¹Ģà¸ķ
    -0.25
     li
    -0.25
    SPATH
    -0.25
     lay
    -0.24
     mai
    -0.24
    POSITIVE LOGITS
    Ñĥк
    0.30
    icing
    0.29
    uve
    0.28
    ry
    0.28
    ural
    0.28
    ures
    0.27
    ure
    0.27
    ured
    0.27
    ub
    0.27
    ulers
    0.27
    Activations Density 1.054%

    No Known Activations