© 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. 57016
    Prev
    Next
    INDEX
    Explanations

    Chicago weather

    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
    åĪ©äºİ
    -0.09
     Champ
    -0.09
    ç©Ĺ
    -0.08
    iston
    -0.08
    esso
    -0.08
    åĪ¨
    -0.08
    .internet
    -0.08
    çĸijä¼¼
    -0.08
    è¶ĬåįĹ
    -0.08
    Cro
    -0.08
    POSITIVE LOGITS
    æļ´é£İ
    0.11
     Blasio
    0.09
     Zy
    0.09
    å¤§åľ°
    0.09
    æ²ĥå°Ķ
    0.09
    大è¿ŀ
    0.09
    åĿļ硬
    0.09
     mafia
    0.09
    rug
    0.08
    lein
    0.08
    Activations Density 0.311%

    No Known Activations