© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89331
    Prev
    Next
    INDEX
    Explanations

    Internet domains and coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹³
    -0.30
    æİĴéĻ¤
    -0.27
     Rangers
    -0.26
    ç¥ł
    -0.26
    _NONNULL
    -0.26
    å¤ĸ交
    -0.26
     found
    -0.25
    ogenic
    -0.25
     didSelect
    -0.24
    .har
    -0.24
    POSITIVE LOGITS
     Pros
    0.26
    æĹ¶æľº
    0.26
    åīįçŀ»æĢ§
    0.26
    ìŀIJê°Ģ
    0.25
    çļĦæĦıä¹ī
    0.25
     Exist
    0.25
     advanced
    0.24
    GRESS
    0.24
     opport
    0.24
    è¿Ļ个游æĪı
    0.24
    Activations Density 6.941%

    No Known Activations