© 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. 61333
    Prev
    Next
    INDEX
    Explanations

    office building or asset

    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
    æ´¾åĩº
    -0.11
    æĶ¾å®½
    -0.10
    åłµ
    -0.10
    è¿Ļ个éĹ®é¢ĺ
    -0.10
    èij©
    -0.10
    åŁ½
    -0.10
    çºĤ
    -0.10
    oen
    -0.10
    COPE
    -0.09
    ç»ıéªĮåĴĮ
    -0.09
    POSITIVE LOGITS
    ä½ĵéĩı
    0.11
    åĨĻåŃĹ楼
    0.10
    åĬŀåħ¬
    0.09
    秣
    0.09
     Merc
    0.09
    秣éĩij
    0.09
    åľŁåľ°
    0.09
    综åIJĪä½ĵ
    0.09
     space
    0.08
    åĩºç§Ł
    0.08
    Activations Density 0.128%

    No Known Activations