© 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. 56770
    Prev
    Next
    INDEX
    Explanations

    wheel and its parts

    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
    ying
    -0.12
    ech
    -0.10
    ðŁı»
    -0.10
     лиÑĪÑĮ
    -0.09
    ../../../
    -0.09
    resse
    -0.09
    æ§İ
    -0.09
    oline
    -0.09
    ion
    -0.09
    té
    -0.09
    POSITIVE LOGITS
    wright
    0.12
    mith
    0.11
    æ¯Ĥ
    0.10
    sets
    0.09
    ings
    0.09
    LESS
    0.09
    åŃIJéĩĮ
    0.09
    /if
    0.09
    -même
    0.09
    ingly
    0.08
    Activations Density 0.017%

    No Known Activations