© 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. 24-TRANSCODER-HP
    7. 151373
    Prev
    Next
    INDEX
    Explanations

    listen

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èµ°åIJij
    -0.45
     towards
    -0.43
     toward
    -0.40
     hÆ°á»Ľng
    -0.38
    åIJijçĿĢ
    -0.37
     Towards
    -0.37
     hacia
    -0.35
     direction
    -0.34
    转åIJij
    -0.33
     directed
    -0.32
    POSITIVE LOGITS
     transgender
    0.26
    åıĺæĢģ
    0.25
     (::
    0.25
    onda
    0.24
    éĹŃ
    0.24
    åĮĻ
    0.23
    æĤ¬
    0.23
    å±Ģéĥ¨
    0.23
    æĺī
    0.23
    Alive
    0.23
    Activations Density 0.987%

    No Known Activations