© 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. 23526
    Prev
    Next
    INDEX
    Explanations

    not

    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
    ActionResult
    -0.27
    éĹ²ç½®
    -0.26
    DO
    -0.26
    åį±å®³
    -0.25
    &S
    -0.25
    å¤ļä½ĻçļĦ
    -0.25
    tractor
    -0.24
     plenty
    -0.24
    do
    -0.24
    lich
    -0.24
    POSITIVE LOGITS
    è¡¡
    0.30
    ign
    0.27
    ä¸įåºĶ该
    0.26
     graceful
    0.25
    -item
    0.24
    ä¸įåı¯éģ¿åħį
    0.24
    esc
    0.24
     esc
    0.24
     fleeting
    0.24
    ITES
    0.24
    Activations Density 0.002%

    No Known Activations