© 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. 37673
    Prev
    Next
    INDEX
    Explanations

    links and changes

    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
    è´¥
    -0.09
    овоÑĢ
    -0.09
     Lomb
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    _SD
    -0.08
    èĪĮå°ĸ
    -0.08
    秤
    -0.08
    æ³ĸ
    -0.08
    erne
    -0.08
     lx
    -0.08
    POSITIVE LOGITS
     baj
    0.10
    åħ«å¹´
    0.09
    å§ij
    0.09
     Nguyên
    0.09
    ä¸ĥå¹´
    0.09
     Bowen
    0.09
    æŀ³
    0.08
    /Framework
    0.08
    aron
    0.08
    .Util
    0.08
    Activations Density 0.003%

    No Known Activations