© 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. 50932
    Prev
    Next
    INDEX
    Explanations

    consistent with

    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
    erial
    -0.10
    ä¸Ģæīĭ
    -0.09
    ä¸įèµ·
    -0.09
    æ»ŀ
    -0.09
    --------------------------------------------------------------------------↵
    -0.08
    .aut
    -0.08
     воÑĤ
    -0.08
    èĤ©èĨĢ
    -0.08
     Licence
    -0.08
     Dias
    -0.08
    POSITIVE LOGITS
    å®ŀéĻħæĥħåĨµ
    0.11
    æĥ¯ä¾ĭ
    0.10
    æ³ķå¾ĭè§Ħå®ļ
    0.10
    å¿ĥæĦı
    0.10
    æĪijå½ĵæŶ
    0.10
    社ä¼ļåıijå±ķ
    0.09
     dõi
    0.09
    å¾Ģ
    0.09
    å¾Ģå¹´
    0.09
    çŃĸ
    0.09
    Activations Density 0.040%

    No Known Activations