© 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. 39420
    Prev
    Next
    INDEX
    Explanations

    in a

    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
    éĤ£ç§į
    -0.10
    åĿŀ
    -0.10
    èįĥ
    -0.09
    çĶļä¹Ī
    -0.09
    ç§ijå°Ķ
    -0.08
    ä¸Ģåı£æ°Ķ
    -0.08
    æŃ£å®Ĺ
    -0.08
    äºĽä»Ģä¹Ī
    -0.08
    á»ģn
    -0.08
    lli
    -0.08
    POSITIVE LOGITS
    强åĮĸ
    0.09
    inton
    0.09
    мÑı
    0.09
    å¤ļå°ij
    0.08
    éļĨ
    0.08
    å§Ķ
    0.08
    qid
    0.08
     ìĿ´ë¥¼
    0.08
    èĮĢ
    0.08
    charge
    0.08
    Activations Density 0.093%

    No Known Activations