© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 64143
    Prev
    Next
    INDEX
    Explanations

    encountering something

    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
    Negative Logits
    -0.13
    ãģĹãģ¾ãģĨ
    -0.11
    ening
    -0.11
    tic
    -0.10
    ickey
    -0.10
    istration
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    ie
    -0.09
    rock
    -0.09
    çon
    -0.09
    POSITIVE LOGITS
    prising
    0.10
    ials
    0.10
    ites
    0.10
    è¡ħ
    0.09
    prises
    0.09
    Ñıми
    0.09
    stood
    0.09
    odings
    0.09
    èĩªå¦Ĥ
    0.09
    ìłĪ
    0.09
    Activations Density 0.009%

    No Known Activations