© 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. 14-TRANSCODER-HP
    7. 39419
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    eba
    -0.30
    ents
    -0.29
    å°±å¤Ł
    -0.26
    urn
    -0.26
    æĻģ
    -0.25
    .untracked
    -0.25
     millis
    -0.25
     Bearing
    -0.25
     hills
    -0.24
    ecx
    -0.24
    POSITIVE LOGITS
    èĥĮ
    0.32
    èĥĮä¸Ĭ
    0.30
    è®°å¿Ĩ
    0.28
    è®°ä½ı
    0.28
    igos
    0.28
    Subset
    0.28
    éģ®
    0.27
    <![
    0.26
    append
    0.26
    为äºĨ
    0.26
    Activations Density 2.714%

    No Known Activations