© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23613
    Prev
    Next
    INDEX
    Explanations

    your [noun]

    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
    èįĩ
    -0.11
    ropp
    -0.10
    æģ¬
    -0.09
    åĩºçĶŁ
    -0.09
    åŃ£
    -0.09
    irable
    -0.09
    ä»ĵ
    -0.09
    äºĨä¸Ģä¸ĭ
    -0.09
    schlä
    -0.08
    åİ¿å§Ķ书记
    -0.08
    POSITIVE LOGITS
    绫
    0.09
    缼
    0.09
    å®ŀå¹²
    0.08
    æį¢
    0.08
    pon
    0.08
    æĿ¥
    0.08
    posix
    0.08
    4
    0.08
    æīĢ以ä»ĸ
    0.08
    สาà¸ĺารà¸ĵ
    0.08
    Activations Density 0.052%

    No Known Activations