© 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. 25-TRANSCODER-HP
    7. 109351
    Prev
    Next
    INDEX
    Explanations

    technical/scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    azon
    -0.28
    èĭĹ
    -0.27
    iminary
    -0.26
    åIJ¸æĶ¶
    -0.26
     Scotia
    -0.26
    arkin
    -0.26
    afort
    -0.26
    verture
    -0.25
    á»ħn
    -0.24
    åIJ¸åħ¥
    -0.24
    POSITIVE LOGITS
    _fg
    0.29
    бл
    0.26
    å·²ä¹ħçļĦ
    0.25
    èĢIJ
    0.25
    æĥ³è¿ĩ
    0.24
     fades
    0.24
     fade
    0.24
     Feder
    0.24
    nodoc
    0.24
    æĪijä¹Ł
    0.23
    Activations Density 0.912%

    No Known Activations