© 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. 38874
    Prev
    Next
    INDEX
    Explanations

    Lincoln City and Avenue

    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
    æľ½
    -0.09
    aka
    -0.09
    uri
    -0.08
    ake
    -0.08
     Sag
    -0.08
    æ®Ĵ
    -0.08
    _PL
    -0.08
    é¢Ĩ导ä¸ĭ
    -0.08
    esy
    -0.08
    çıį
    -0.08
    POSITIVE LOGITS
    shire
    0.14
    åľ¨ç¾İåĽ½
    0.10
    è¦ģæĬĬ
    0.10
    åĬĽè¿ĺæĺ¯
    0.10
    ¼
    0.09
    åĽŀ头
    0.09
    æİ·
    0.09
    onian
    0.09
    åľ¨åħ¨çIJĥ
    0.09
    è´«è¡Ģ
    0.09
    Activations Density 0.002%

    No Known Activations