© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19831
    Prev
    Next
    INDEX
    Explanations

    season, timing, and dates

    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
    ISC
    -0.12
     пÑģ
    -0.11
    ILI
    -0.10
    åį°ç«ł
    -0.09
    ascar
    -0.09
    èľľ
    -0.09
    éĵħ
    -0.09
    resent
    -0.09
    è°©
    -0.09
    ubber
    -0.09
    POSITIVE LOGITS
    æİ¨è¿Ł
    0.12
    æľĢæĹ©
    0.12
    æĹ©æĻļ
    0.11
    æıIJåīį
    0.11
    æľĢæĹ©çļĦ
    0.11
    æıIJæĹ©
    0.11
    å»¶è¿Ł
    0.11
    .runtime
    0.10
     earliest
    0.09
    æĹ©æĹ©
    0.09
    Activations Density 0.069%

    No Known Activations