© 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. 2505
    Prev
    Next
    INDEX
    Explanations

    Voice of

    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
    åĹĮ
    -0.08
    éĴ³
    -0.08
    举
    -0.08
    æģ¶å¿ĥ
    -0.08
    Assembler
    -0.07
    æģ¶æĢ§
    -0.07
    èĬĤ
    -0.07
    -Sah
    -0.07
    ities
    -0.07
     yesterday
    -0.07
    POSITIVE LOGITS
    çľ¼çļ®
    0.10
    odyn
    0.10
    ocos
    0.10
    иÑĢов
    0.09
    LineStyle
    0.09
    çIJ´
    0.09
    çĬį
    0.09
    ÐIJÐĿ
    0.09
    _redis
    0.09
    IDDEN
    0.09
    Activations Density 0.003%

    No Known Activations