© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    get or receive

    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
    æĭĽå¾ħ
    -0.09
    ç®ķ
    -0.09
    æ¡ĥèĬ±
    -0.09
    ä¼Ĭæĸ¯
    -0.09
    çĶŁçĹħ
    -0.09
    éĻ¶
    -0.09
    座
    -0.09
    å®ŀæĸ½
    -0.09
    gien
    -0.08
    女æĺŁ
    -0.08
    POSITIVE LOGITS
    ä»ĺåĩº
    0.11
    å¾ĹåĪ°
    0.10
     пÑĢеимÑĥÑīеÑģÑĤв
    0.09
    ç¡®
    0.08
    _procs
    0.08
    èİ·å¾Ĺ
    0.08
    ONO
    0.08
     Latest
    0.08
    å®ŀæĥł
    0.08
    æĤ¨å¥½
    0.08
    Activations Density 0.193%

    No Known Activations