© 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. 36707
    Prev
    Next
    INDEX
    Explanations

    anyway, least, course, obviously

    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
    级åĪ«çļĦ
    -0.08
    erval
    -0.08
    _AF
    -0.08
    BP
    -0.08
    Õ²
    -0.08
    Fant
    -0.08
    åģĥ
    -0.08
    KER
    -0.08
     Feder
    -0.08
     ordinal
    -0.08
    POSITIVE LOGITS
    èĩªè´Ł
    0.10
    iami
    0.10
    ç»Ĵ
    0.10
    èĢĮè¨Ģ
    0.09
    åijĹ
    0.09
    uÃŃ
    0.09
    è¯ļä¿¡
    0.09
    çºĮ
    0.09
    è°±
    0.09
    å±
    0.09
    Activations Density 0.046%

    No Known Activations