© 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. 52125
    Prev
    Next
    INDEX
    Explanations

    absence of

    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¸įéĶĻçļĦ
    -0.10
     unh
    -0.09
    æĿ¥ä¸įåıĬ
    -0.09
    stuff
    -0.09
    ẳng
    -0.09
    ERS
    -0.09
    ewn
    -0.08
    å¦Ĥæŀľä¸į
    -0.08
    ully
    -0.08
    åķIJ
    -0.08
    POSITIVE LOGITS
    äºİ
    0.10
    äºĨä¸Ģ个
    0.10
    羣æŃ£çļĦ
    0.10
    ees
    0.10
    å·²ä¹ħçļĦ
    0.09
    æ®Ĩ
    0.09
    äºĨä¸Ģ声
    0.09
    deny
    0.09
    åĴĮåıijå±ķ
    0.09
    æ°Ľ
    0.09
    Activations Density 0.021%

    No Known Activations