© 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. 10002
    Prev
    Next
    INDEX
    Explanations

    franchise locations

    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
    太æŀģ
    -0.10
    æģ¶
    -0.09
    å¯ĵ
    -0.09
    西æ´ĭ
    -0.08
    å¢ŀè¿Ľ
    -0.08
    åħ¬åħ±åľºæīĢ
    -0.08
     tame
    -0.08
     whichever
    -0.08
     rud
    -0.08
    åĽ¢ä½ĵ
    -0.08
    POSITIVE LOGITS
    åĬłçĽŁ
    0.12
    åĬłçĽŁåķĨ
    0.12
    åĥĸ
    0.10
     franchise
    0.10
    å¤ļåľ°
    0.10
    ç¾İ容
    0.10
    æī¶æĮģ
    0.09
     franch
    0.09
    è¿ŀéĶģ
    0.09
    æŃ¥
    0.09
    Activations Density 0.039%

    No Known Activations