© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 55162
    Prev
    Next
    INDEX
    Explanations

    retro computers and gaming platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <tag
    -0.09
    гÑĢан
    -0.09
    æŃ¢
    -0.09
     tanker
    -0.09
    /apache
    -0.09
     sunglasses
    -0.08
    Crow
    -0.08
     mắt
    -0.08
    Fuse
    -0.08
     Chá»ĭ
    -0.08
    POSITIVE LOGITS
    ÑĮÑİ
    0.11
    管å±Ģ
    0.10
     ROM
    0.09
    æĬ¥è®°èĢħ
    0.09
    å°ıå¾®
    0.09
     Atari
    0.09
    éĩįçĶŁ
    0.09
    eprom
    0.09
    SPEC
    0.09
    SCII
    0.09
    Activations Density 0.127%

    No Known Activations