© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53539
    Prev
    Next
    INDEX
    Explanations

    hesitate to

    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
    ä¸įåıĺ
    -0.09
    olle
    -0.09
    é«»
    -0.08
    vo
    -0.08
    é»ĺ
    -0.08
    ä»İ容
    -0.08
    _tem
    -0.08
     undes
    -0.08
    ä¸įåı¯
    -0.08
    abay
    -0.08
    POSITIVE LOGITS
    åķ¬
    0.11
    æ®Ħ
    0.10
    åĪ°ä½į
    0.10
    ãĥĭãĤ¢
    0.09
    èĩ
    0.09
    为客æĪ·
    0.09
    æĪij以为
    0.09
    æĭ¿èµ·
    0.09
    ä¹ĭåĬĽ
    0.09
    ä¸Ĭè°ĥ
    0.09
    Activations Density 0.004%

    No Known Activations