© 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. 9-TRANSCODER-HP
    7. 30259
    Prev
    Next
    INDEX
    Explanations

    fascinating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     quoi
    -0.26
    ä¸ĩè¾Ĩ
    -0.26
    æĹ¥åĨħ
    -0.25
     targets
    -0.24
     Marin
    -0.24
    igt
    -0.24
     UPC
    -0.24
    targets
    -0.24
    æķĪ
    -0.23
    sym
    -0.23
    POSITIVE LOGITS
    lasting
    0.28
    çļĦ人çĶŁ
    0.28
    åĨĴ
    0.27
    amax
    0.26
     Hammond
    0.25
    rias
    0.25
    piring
    0.25
    çļĦ羣å®ŀ
    0.25
     comps
    0.24
    éĢļ常æĺ¯
    0.24
    Activations Density 0.390%

    No Known Activations