© 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. 4745
    Prev
    Next
    INDEX
    Explanations

    Shasta, Shoshone, Kirby, Waco, Oshkosh

    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
    åıĪ好åıĪå¿«
    -0.09
    è·»
    -0.09
    azel
    -0.09
     пиÑĤ
    -0.09
    chè
    -0.09
    çłŃ
    -0.09
    çĶŁçĶŁ
    -0.09
    窨
    -0.09
    senal
    -0.09
    iday
    -0.09
    POSITIVE LOGITS
    ä¸Ģåı£æ°Ķ
    0.08
    èĺĸ
    0.08
    ç´ł
    0.08
    æŁı
    0.08
    æ¼Ķç»İ
    0.08
    urb
    0.08
     bite
    0.08
    /or
    0.08
    åĻĻ
    0.08
    Outcome
    0.08
    Activations Density 0.038%

    No Known Activations