© 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. 33273
    Prev
    Next
    INDEX
    Explanations

    effect change

    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
    髦
    -0.10
    èĢĥéªĮ
    -0.09
    人æ°ijæľįåĬ¡
    -0.08
    æį§
    -0.08
     Sno
    -0.08
    åĶIJå±±
    -0.08
    itto
    -0.07
    apon
    -0.07
    æĹ¥åIJİ
    -0.07
    usb
    -0.07
    POSITIVE LOGITS
     change
    0.11
     Change
    0.10
    è¯īæ±Ĥ
    0.10
    change
    0.10
    åIJ¸
    0.09
    æĶ¿çŃĸ
    0.09
    æµİ
    0.09
    æĶ¹åıĺ
    0.09
    æĽ´æĶ¹
    0.09
    Change
    0.09
    Activations Density 0.099%

    No Known Activations