© 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. 35490
    Prev
    Next
    INDEX
    Explanations

    join us

    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
    ç½Ķ
    -0.10
    tier
    -0.10
    ınt
    -0.09
     tiếng
    -0.09
     McKay
    -0.08
    ensing
    -0.08
    åºķæ°Ķ
    -0.08
    åĽ½å®ī
    -0.08
    åİĨåı²æĸ°
    -0.08
    ãģĵãģĵãģ¾ãģ§
    -0.08
    POSITIVE LOGITS
    æĪij们çļĦ
    0.18
    æĪij们
    0.18
    æĪijä»¬åľ¨
    0.15
     our
    0.13
    æĪijåĢij
    0.13
    æĪijä»¬ä¹Ł
    0.13
    æĪij们就
    0.13
    æĪij们ä¼ļ
    0.13
    æĺ¯æĪij们
    0.12
     наÑĪиÑħ
    0.12
    Activations Density 0.118%

    No Known Activations