© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37035
    Prev
    Next
    INDEX
    Explanations

    newspaper names

    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
    åįķ车
    -0.12
    客æłĪ
    -0.10
    çĽ¸å¯¹äºİ
    -0.10
    çĹ´è¿·
    -0.09
    è¿ĺæĺ¯
    -0.09
    è¿IJæ°Ķ
    -0.09
    ÑģÑĤи
    -0.09
    ifest
    -0.09
    å¿ĥåĬ¨
    -0.09
    Ñģли
    -0.09
    POSITIVE LOGITS
     Spare
    0.09
    è¹ij
    0.09
    éģ®
    0.08
    æĪĽ
    0.08
    Caller
    0.08
    _Sh
    0.08
    ocos
    0.08
    彩
    0.08
    sembler
    0.08
    creens
    0.08
    Activations Density 0.014%

    No Known Activations