© 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. 23641
    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
    æ½ľ
    -0.27
    ourg
    -0.27
    orig
    -0.27
    ç¥Ľ
    -0.26
     verified
    -0.26
    çĿ«
    -0.25
    ^^^^
    -0.25
    drv
    -0.25
    quil
    -0.25
    éħĮ
    -0.24
    POSITIVE LOGITS
    éĩijåŃĹå¡Ķ
    0.28
    olla
    0.27
    scriptId
    0.27
    é½Ĭ
    0.26
    loh
    0.26
    MEM
    0.26
    )b
    0.25
    伯
    0.25
    MMdd
    0.24
    Injection
    0.24
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.