© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52962
    Prev
    Next
    INDEX
    Explanations

    reach out / reach me

    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
    pn
    -0.09
    æ¯ķç«Ł
    -0.09
    èĩ³ä»Ĭ
    -0.08
     Weber
    -0.08
     mush
    -0.08
    åIJ¦
    -0.08
    etCode
    -0.08
     distort
    -0.07
    åĮĹæĸ¹
    -0.07
    社ä¼ļåıijå±ķ
    -0.07
    POSITIVE LOGITS
    èģĶç³»
    0.12
    çľĭæ³ķ
    0.11
    éĨ®
    0.10
    请èģĶç³»
    0.10
    æĹłæīĢè°ĵ
    0.09
    Õ°
    0.09
    .cross
    0.09
     contacts
    0.09
    çļĦçľĭæ³ķ
    0.09
    ç½ijåĿĢ
    0.09
    Activations Density 0.024%

    No Known Activations