© 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. 58355
    Prev
    Next
    INDEX
    Explanations

    DOCTYPE html

    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
    ials
    -0.09
    /desktop
    -0.09
    éĩįå¤į
    -0.09
    fast
    -0.09
    ware
    -0.09
    çĸ²åĬ³
    -0.09
    èī°èĭ¦
    -0.09
    aket
    -0.09
    rapid
    -0.09
    鼩
    -0.08
    POSITIVE LOGITS
     Griffin
    0.09
     pit
    0.09
    æľīèī²
    0.09
    æĹłæĥħ
    0.08
     pity
    0.08
    ä»Ķç»Ĩ
    0.08
    .SET
    0.08
     Fu
    0.08
    ths
    0.08
     Pit
    0.08
    Activations Density 0.138%

    No Known Activations