© 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. 34877
    Prev
    Next
    INDEX
    Explanations

    mix and add

    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
     Angeles
    -0.09
    esk
    -0.09
     lone
    -0.08
    è¯¾æľ¬
    -0.08
    客æĪ¿
    -0.08
    èµĦ
    -0.08
     Alone
    -0.08
    çªģå¦Ĥåħ¶æĿ¥
    -0.08
    istine
    -0.08
     localVar
    -0.08
    POSITIVE LOGITS
    åħ±åIJĮåıijå±ķ
    0.09
    è°ĥéħį
    0.09
    ä»Ģ
    0.09
    æĶ¯æĮģåĬĽåº¦
    0.08
    æīĵæĭ¼
    0.08
    è¾Ĺ
    0.08
    åħ±åIJĮ
    0.08
    çĦĸ
    0.08
     latter
    0.08
    èĢĻ
    0.08
    Activations Density 0.018%

    No Known Activations