© 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. 20-TRANSCODER-HP
    7. 62735
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ibbon
    -0.27
    å·¾
    -0.26
    -collar
    -0.26
     borne
    -0.25
    vet
    -0.25
    ween
    -0.25
    contri
    -0.25
     kı
    -0.25
    ŀĭ
    -0.24
    ä¿ĿåŃĺ
    -0.24
    POSITIVE LOGITS
    æĹłè¾ľ
    0.26
     expectation
    0.25
    è¿Ļæĺ¯æĪij们
    0.25
     gast
    0.25
    ãĥĩãĤ£ãĥ³ãĤ°
    0.24
    _EXPECT
    0.24
     shot
    0.24
    .fm
    0.24
    ä¹ĭ称
    0.24
    ore
    0.24
    Activations Density 56.966%

    No Known Activations