© 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. 4573
    Prev
    Next
    INDEX
    Explanations

    code example and technical question

    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
    åIJī祥
    -0.09
    åIJŃ
    -0.09
    çķı
    -0.09
    æ··ä¹±
    -0.09
    æĥij
    -0.09
    寸
    -0.08
    å½±éŁ³
    -0.08
    è§ľ
    -0.08
    åħĨ
    -0.08
    æĤ¸
    -0.08
    POSITIVE LOGITS
    ãģĵãģĵãģ¾ãģ§
    0.09
    EMU
    0.08
     McM
    0.08
    è¢Ń
    0.08
    åħ¼
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
    èĵIJ
    0.08
    esor
    0.08
    åħ¬ç½ijå®īå¤ĩ
    0.08
    jom
    0.08
    Activations Density 0.294%

    No Known Activations