© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8769
    Prev
    Next
    INDEX
    Explanations

    standard deviation

    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
     ant
    -0.10
    è°³
    -0.10
    ieber
    -0.09
     иÑģÑĤоÑĩник
    -0.09
    åijĬ
    -0.08
    íĥĿ
    -0.08
    èĵĦ
    -0.08
     Plate
    -0.08
    çĸijéļ¾
    -0.08
    好转
    -0.08
    POSITIVE LOGITS
    èĪĴ
    0.10
    åIJ¬è¿ĩ
    0.09
    วà¸ĩ
    0.09
    èĩªæ²»
    0.09
    APE
    0.09
    宸
    0.09
    hes
    0.09
    andard
    0.09
    æĺī
    0.09
    repos
    0.08
    Activations Density 0.082%

    No Known Activations