© 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. 56802
    Prev
    Next
    INDEX
    Explanations

    relates to

    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
     nearby
    -0.08
    以æѤ
    -0.08
    ä¸ĩ家
    -0.08
    indr
    -0.08
     LANG
    -0.08
    åħ«åŃĹ
    -0.08
     Cent
    -0.08
    åĨĴåĩº
    -0.08
    æŁ¥
    -0.08
    abbr
    -0.08
    POSITIVE LOGITS
    ady
    0.10
    çĹ¼
    0.10
    åħĢ
    0.09
    çĭłæĬĵ
    0.09
    è§Ħ模æľĢ大
    0.09
    è¿Ļä¸Ģ天
    0.09
    èī²ç´ł
    0.09
    çļĦçľ¼åħī
    0.09
    æľºåĻ¨
    0.09
    å½±åĵįåĬĽçļĦ
    0.08
    Activations Density 0.163%

    No Known Activations