© 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. 24-TRANSCODER-HP
    7. 149135
    Prev
    Next
    INDEX
    Explanations

    Time and Schedule

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    rô
    -0.27
    )(__
    -0.27
    ROID
    -0.26
    ứng
    -0.26
    urers
    -0.26
    edBy
    -0.25
    ä¸IJ
    -0.25
    éħµ
    -0.25
    [${
    -0.25
    unic
    -0.25
    POSITIVE LOGITS
     reopening
    0.29
    esis
    0.28
     closing
    0.27
    val
    0.27
    closing
    0.25
    æīĵå¼Ģ
    0.25
     gros
    0.25
    ãģĤãĤĭ
    0.25
    0.25
     tails
    0.25
    Activations Density 0.182%

    No Known Activations