© 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. 10173
    Prev
    Next
    INDEX
    Explanations

    basis for

    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
    ing
    -0.09
    èĤ¡
    -0.08
    AGING
    -0.08
    æŁIJäºĽ
    -0.08
    æľī幸
    -0.07
    chn
    -0.07
    hatt
    -0.07
    æģ°å¥½
    -0.07
     Jack
    -0.07
    aman
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.11
    ä»ģ
    0.11
    éĤĽ
    0.10
    é»İæĺİ
    0.10
    缴èIJ¥
    0.09
    atical
    0.09
    åģ¥åº·ç®¡çIJĨ
    0.09
    èĸ®
    0.09
    çĭİ
    0.09
    æ¯įå©´
    0.09
    Activations Density 0.014%

    No Known Activations