© 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. 27-TRANSCODER-HP
    7. 9808
    Prev
    Next
    INDEX
    Explanations

    Foreign characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ensor
    -0.26
    鬥
    -0.26
    çĽı
    -0.25
     vá
    -0.25
    åĴª
    -0.24
    èѦæĥķ
    -0.24
     Abbas
    -0.24
    ãĤ¤ãĥĪ
    -0.24
    arı
    -0.23
    èĭ¥æľī
    -0.23
    POSITIVE LOGITS
    æīĢåľ¨åľ°
    0.29
    _NEAR
    0.27
     tails
    0.27
     surrounding
    0.27
    rear
    0.26
    _near
    0.26
    tails
    0.26
    ade
    0.26
    åħħåĪĨåıijæĮ¥
    0.26
     adjoining
    0.25
    Activations Density 0.000%

    No Known Activations