© 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. 36426
    Prev
    Next
    INDEX
    Explanations

    brands

    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
    åĨį说
    -0.11
    âĿģ
    -0.09
    lander
    -0.09
    IMER
    -0.08
    å¹³åĿĩæ°´å¹³
    -0.08
    wend
    -0.08
    票
    -0.08
    缸åıį
    -0.08
    _evaluation
    -0.08
    è´´
    -0.08
    POSITIVE LOGITS
    æłĩè¯Ĩ
    0.10
    åIJįçīĮ
    0.09
    hood
    0.09
    éķĩæ±Ł
    0.09
    çijķ
    0.09
    ç»
    0.09
    .coll
    0.09
     ampl
    0.09
    èĩªåľ¨
    0.08
    camel
    0.08
    Activations Density 0.021%

    No Known Activations