© 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. 58867
    Prev
    Next
    INDEX
    Explanations

    saying or telling

    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
    å»ºåĽ½
    -0.10
    èĢģé¾Ħ
    -0.09
    å½¢æĪIJäºĨ
    -0.09
    æ²±
    -0.08
    ä¿¡èµĸ
    -0.08
    è´²
    -0.08
     Ont
    -0.08
    Steam
    -0.08
    å¸ģ
    -0.08
    大æĪ·
    -0.08
    POSITIVE LOGITS
    ä¸Ģ声
    0.10
    anner
    0.09
    ewn
    0.09
    仲è£ģ
    0.09
    说ä»Ģä¹Ī
    0.09
    UBL
    0.08
    émon
    0.08
     ÐĴам
    0.08
    æ£Ģå¯Łå®ĺ
    0.08
    mouth
    0.08
    Activations Density 0.016%

    No Known Activations