© 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. 23-TRANSCODER-HP
    7. 25416
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     teams
    -0.27
    ids
    -0.27
    _UUID
    -0.27
    UUID
    -0.26
    ÅĤ
    -0.26
     UUID
    -0.25
    .cfg
    -0.25
    achs
    -0.24
     libraries
    -0.24
    (UUID
    -0.24
    POSITIVE LOGITS
    贯彻èIJ½å®ŀ
    0.31
    åıijå±ķæ½ľåĬĽ
    0.29
    æŀŃ
    0.27
    ç¨ĭ度
    0.27
    æļĹ示
    0.27
     sacrific
    0.27
    çļĦéģĵçIJĨ
    0.27
    è¿ĻäºĽéĹ®é¢ĺ
    0.26
    æ²»å®ī
    0.26
    gression
    0.26
    Activations Density 0.034%

    No Known Activations