© 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. 56783
    Prev
    Next
    INDEX
    Explanations

    reasonably / fairly / relatively

    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
    ymi
    -0.09
     canv
    -0.08
    åѦåīį
    -0.08
    åħ³éĶ®æĺ¯
    -0.08
    ç¿°
    -0.08
    æĽ´
    -0.08
    tlement
    -0.08
     clearer
    -0.08
    æ¸ħåįİ
    -0.08
    oom
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.14
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.14
    ä¸įéĶĻ
    0.13
    æĺ¯æ¯Ķè¾ĥ
    0.12
    è¾ĥ好çļĦ
    0.11
    ä¹Łæ¯Ķè¾ĥ
    0.11
    æĿ¥è®²
    0.11
    å¹´è½»
    0.11
    稳å®ļçļĦ
    0.10
    è¾ĥå¿«
    0.10
    Activations Density 0.176%

    No Known Activations