© 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. 17703
    Prev
    Next
    INDEX
    Explanations

    joins clauses or lists

    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
    åħ®
    -0.08
    并äºİ
    -0.08
    éľĨ
    -0.08
    ?key
    -0.08
    ç¼Ľ
    -0.08
    unden
    -0.08
    çĭŃ
    -0.08
    либо
    -0.08
    ungen
    -0.08
     respectively
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·ä¸ĢæĿ¥
    0.09
    åħ¬å®īå±Ģ
    0.08
    ç»Ī
    0.08
    éĤ£ä¸ªæŶåĢĻ
    0.08
    UAGE
    0.08
    è¿Ļæł·æīįèĥ½
    0.08
    åľ¨è¿Ļç§į
    0.08
    æ°ijèIJ¥
    0.08
    æĸ§
    0.08
    两èĢħ
    0.08
    Activations Density 0.045%

    No Known Activations