© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37802
    Prev
    Next
    INDEX
    Explanations

    signed or unsigned text

    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
    ä¸İä¸ŃåĽ½
    -0.09
    enders
    -0.09
    å±¥
    -0.09
    æ§
    -0.09
    æĹłæĥħ
    -0.09
    bere
    -0.09
    縳
    -0.09
    èĥŃ
    -0.09
    ç³Ł
    -0.09
    ä¸İåħ¶
    -0.09
    POSITIVE LOGITS
    ity
    0.09
    onis
    0.09
    IRECTION
    0.09
    keit
    0.08
    满äºĨ
    0.08
     اÙĦعشر
    0.08
    åį±
    0.08
    çĿĢ
    0.07
    åįģ大
    0.07
    nowled
    0.07
    Activations Density 0.012%

    No Known Activations