© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    in a debut movie

    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
    åĪ°å¤Ħ
    -0.08
    æķħå±ħ
    -0.08
    æĹ·
    -0.08
    ä¸Ŀ
    -0.08
     Visitor
    -0.08
    课
    -0.08
    èįĥ
    -0.08
    åķĸ
    -0.08
     guided
    -0.08
    é¦Ĩ
    -0.08
    POSITIVE LOGITS
    é¢ł
    0.11
    åĩºéģĵ
    0.10
    thal
    0.10
    огÑĢаÑĦ
    0.10
    åħĪ导
    0.09
    ÑģÑĥ
    0.09
    è£½ä½ľ
    0.09
     ì¶
    0.09
    åĪ¶ä½ľ
    0.09
    çŃ¹åĪĴ
    0.09
    Activations Density 0.143%

    No Known Activations