© 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. 38741
    Prev
    Next
    INDEX
    Explanations

    hotel and plaza names

    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
    ä¸Ńåħ±ä¸Ń央
    -0.10
    ä¹ĭå¿ĥ
    -0.09
    æĸ°å½¢åĬ¿
    -0.09
    enga
    -0.09
     Griff
    -0.09
    à¹Ģหล
    -0.08
    æ²»çĹħ
    -0.08
    æİ£
    -0.08
    èĪĢ
    -0.08
    åĨħéĺģ
    -0.08
    POSITIVE LOGITS
    å°Ķæĸ¯
    0.10
    å¾Ģå¹´
    0.09
    管çIJĨåĬŀæ³ķ
    0.09
    é¬ĵ
    0.09
    æľĪä¸Ń
    0.08
    олж
    0.08
     yakın
    0.08
     ITE
    0.08
    éĦ¯
    0.08
     Yak
    0.08
    Activations Density 0.004%

    No Known Activations