© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    especially when

    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¦ģä¹Ī
    -0.11
    åħ±æľī
    -0.10
    好åIJĹ
    -0.10
    å½ĵçĦ¶
    -0.09
    éĶµ
    -0.09
    æĹ¢æĺ¯
    -0.09
     either
    -0.09
    主è¦ģæľī
    -0.09
     вполне
    -0.09
    avenport
    -0.09
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.12
    sic
    0.09
    æīİ
    0.09
     after
    0.08
     Enlight
    0.08
     randomized
    0.08
     when
    0.08
    çķ¶æĤ¨
    0.08
    ially
    0.08
    以åIJİ
    0.08
    Activations Density 0.023%

    No Known Activations