© 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. 32503
    Prev
    Next
    INDEX
    Explanations

    violate rules or limits

    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¸įçķĻ
    -0.09
    vid
    -0.09
     Succ
    -0.08
    æݨå¼Ģ
    -0.08
    çĦ¦
    -0.08
    çIJĨäºĭ
    -0.08
    -linux
    -0.08
    éŨæĪ·ç½ijç«Ļ
    -0.08
    oked
    -0.08
     oneself
    -0.08
    POSITIVE LOGITS
    éģµå®Ī
    0.09
    chie
    0.09
    鸽
    0.09
    è¿Ŀåıį
    0.09
    è¹Ī
    0.09
    åĪ«äººçļĦ
    0.09
     violation
    0.08
    idth
    0.08
    èij±
    0.08
    éģķåıį
    0.08
    Activations Density 0.020%

    No Known Activations