© 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. 33-TRANSCODER-HP
    7. 52868
    Prev
    Next
    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åij½è¿IJ
    -0.31
    inté
    -0.26
    verbatim
    -0.26
    embers
    -0.25
    ini
    -0.25
    empt
    -0.25
    æ±²
    -0.25
    ç»Ī
    -0.24
    incy
    -0.24
     annoying
    -0.23
    POSITIVE LOGITS
     hor
    0.28
     bil
    0.28
     tun
    0.27
    æĥ³ä¸įåĪ°
    0.26
     bic
    0.26
     sik
    0.26
     pos
    0.25
    ä¼łåĩº
    0.25
     s
    0.25
     cap
    0.24
    Activations Density 0.001%

    No Known Activations