© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21172
    Prev
    Next
    INDEX
    Explanations

    simple, asymmetric, objects, just

    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
    æľºæ¢°åĮĸ
    -0.11
    èĮ§
    -0.09
    /lic
    -0.09
    çŃ
    -0.09
    çݰ代åĮĸ
    -0.09
    ä¸Ģåī¯
    -0.09
    ä¸įä»ħä»ħæĺ¯
    -0.08
    ýt
    -0.08
     RedirectTo
    -0.08
    æľ«
    -0.08
    POSITIVE LOGITS
     informal
    0.15
    åı£å¤´
    0.13
    èĩªåıij
    0.12
    åĩŃ
    0.11
    åĩŃåĢŁ
    0.11
    æķ£
    0.11
    ä¾ĿéĿł
    0.10
    èĩªè¡Į
    0.10
    临æĹ¶
    0.10
     ê·¸ëĥ¥
    0.10
    Activations Density 0.391%

    No Known Activations