© 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. 8646
    Prev
    Next
    INDEX
    Explanations

    cumulative or cum

    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
    enie
    -0.09
     GSL
    -0.09
    çıħ
    -0.09
    åĨħ马
    -0.08
    ابة
    -0.08
    anga
    -0.08
    é¼İ
    -0.08
    ëĵĿ
    -0.08
    Charsets
    -0.08
    åīįä¸ĸ
    -0.08
    POSITIVE LOGITS
    �t
    0.09
    ious
    0.09
    对æĸ¹
    0.09
    bersome
    0.09
    DBG
    0.08
     вÑģеÑħ
    0.08
    æĸĩåĮĸèīºæľ¯
    0.08
    cum
    0.08
    æĬ¥åIJį
    0.08
    为æŃ¢
    0.08
    Activations Density 0.005%

    No Known Activations