© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36883
    Prev
    Next
    INDEX
    Explanations

    how to use words

    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
    éĥ¨åī¯éĥ¨éķ¿
    -0.11
    为ä¹ĭ
    -0.09
    ãģĻãģ¹
    -0.09
    èħ°
    -0.09
     XCT
    -0.09
    è°ĵ
    -0.09
    åĭ¿
    -0.09
    åıªå¥½
    -0.08
    holm
    -0.08
    åħ¬åħ±æľįåĬ¡
    -0.08
    POSITIVE LOGITS
    оÑģоб
    0.10
    ï¸
    0.10
    mere
    0.09
    /if
    0.09
    çľĭå¾ħ
    0.08
    ä¸ĢæŃ¥æŃ¥
    0.08
    ÑĪÑĥ
    0.08
    è¿¥
    0.08
    æ´¾
    0.08
     Others
    0.08
    Activations Density 0.134%

    No Known Activations