© 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. 50220
    Prev
    Next
    INDEX
    Explanations

    playable cast, fighting fighter

    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
    鲸
    -0.09
    éľ
    -0.09
    驼
    -0.09
    æļĹ
    -0.09
    ãĤŃãĥ³ãĤ°
    -0.08
    çĬ¬
    -0.08
     phục
    -0.08
     tÆ°á»Ŀng
    -0.08
    kker
    -0.08
     Musk
    -0.08
    POSITIVE LOGITS
    çĪ¶åŃIJ
    0.10
    fault
    0.09
    åĬŁå¤«
    0.09
    ÑĨов
    0.09
     fault
    0.09
    lyph
    0.08
    ç¥Ĺ
    0.08
    èĭķ
    0.08
    èļ¬
    0.08
    ä¸ī人
    0.08
    Activations Density 0.158%

    No Known Activations