© 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. 32852
    Prev
    Next
    INDEX
    Explanations

    damn, freaking, pain, out, manga

    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
    èĶļ
    -0.10
    ç¨ļ
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    ÙĤات
    -0.09
    è·»
    -0.08
    嵩
    -0.08
    å¾Īé«ĺåħ´
    -0.08
    æī¹åĩĨ
    -0.08
    éľ²å¤©
    -0.08
    assignments
    -0.08
    POSITIVE LOGITS
    å¼Ģä¼ļ
    0.09
    缸å½ĵ
    0.08
    /wp
    0.08
    åıij声
    0.08
    ä¹ĸ
    0.08
    çŃĸ
    0.08
    çĥĺ
    0.08
     示
    0.08
    åĪ°åľº
    0.08
    aty
    0.08
    Activations Density 0.065%

    No Known Activations