© 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. 25361
    Prev
    Next
    INDEX
    Explanations

    Resting, sleep

    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
    ç´§
    -0.28
    ä¼ģ
    -0.27
    å¼ķ
    -0.27
    lag
    -0.27
    导
    -0.26
    çļĦç¡®
    -0.26
    .INSTANCE
    -0.25
    å®ŀä½ĵ
    -0.25
    ç¿Ķ
    -0.25
    åĴĸåķ¡
    -0.25
    POSITIVE LOGITS
    ares
    0.30
    ections
    0.28
    izon
    0.27
    xis
    0.27
    设ç«ĭäºĨ
    0.26
    ation
    0.26
    ity
    0.24
    év
    0.24
    gue
    0.24
    èĥ½æī¾åĪ°
    0.24
    Activations Density 0.007%

    No Known Activations