© 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. 21594
    Prev
    Next
    INDEX
    Explanations

    version numbers after 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
    çݳ
    -0.10
    åĪĹåħ¥
    -0.09
    æķ¦
    -0.09
    æī«ä¸Ģ
    -0.09
    è¿ĵ
    -0.09
    ä¸Ģè·¯
    -0.08
    _dispatcher
    -0.08
    Ëij
    -0.08
    \\.
    -0.08
     bible
    -0.08
    POSITIVE LOGITS
     Forums
    0.08
    è·Łå¥¹
    0.08
    é¢ĸ
    0.08
    TargetException
    0.08
    è·Ł
    0.08
    Vect
    0.07
    çģĮ
    0.07
    åijķ
    0.07
    ono
    0.07
    ials
    0.07
    Activations Density 0.151%

    No Known Activations