© 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. 11599
    Prev
    Next
    INDEX
    Explanations

    could use to achieve goal

    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
    ardi
    -0.10
    ä¸ŃåĽ½åĽ½éĻħ
    -0.09
     reap
    -0.08
    åĿ¦
    -0.08
    alk
    -0.07
    ä¸įèĤ¯
    -0.07
     Crossing
    -0.07
    acci
    -0.07
    ube
    -0.07
    ning
    -0.07
    POSITIVE LOGITS
    è§Ĥåħī
    0.10
    ì´ī
    0.09
    åįģæĿ¡
    0.09
    EAR
    0.09
    ilib
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    èĹ
    0.09
    isclosed
    0.09
    uplicate
    0.09
    ìĦ
    0.08
    Activations Density 0.037%

    No Known Activations