© 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. 58592
    Prev
    Next
    INDEX
    Explanations

    in the past

    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
    æ¯ı次
    -0.08
     вид
    -0.08
     má»ĩnh
    -0.08
     inaugural
    -0.08
     slightest
    -0.08
    Hack
    -0.08
    æģķ
    -0.08
     sess
    -0.08
    adic
    -0.07
    ether
    -0.07
    POSITIVE LOGITS
    åĩłå¹´
    0.11
    æľ¬ç½ij
    0.11
    æı©
    0.10
    åĴİ
    0.09
    uentes
    0.09
    ä¿Ŀåį«
    0.09
    ule
    0.09
    lege
    0.08
    峪
    0.08
    æĬĬæĪij
    0.08
    Activations Density 0.011%

    No Known Activations