© 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. 25458
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ORIZED
    -0.27
    辫
    -0.27
     Cla
    -0.26
    è´¿
    -0.25
    ç±³å°Ķ
    -0.25
    trap
    -0.25
    RS
    -0.25
    æ¡£
    -0.24
     adaptation
    -0.23
     adapt
    -0.23
    POSITIVE LOGITS
     expectations
    0.33
     expectation
    0.30
    expect
    0.27
    æļ´
    0.27
    Expect
    0.26
     compliments
    0.25
    éĿŀæ³ķ
    0.25
    inis
    0.24
    ä¸įå®Į
    0.24
     deficiencies
    0.24
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.