© 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. 56553
    Prev
    Next
    INDEX
    Explanations

    careers exchanged

    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
    æĬĵ好
    -0.09
    emat
    -0.08
    奢
    -0.08
    ille
    -0.08
    åįłæį®
    -0.08
    è¶³å¤Ł
    -0.08
    çĽĽå¤§
    -0.08
    æĮĤçĿĢ
    -0.08
    æĹłç¼Ŀ
    -0.08
    ç¥Ľ
    -0.08
    POSITIVE LOGITS
     dabei
    0.13
    åľ¨è¿Ļ
    0.11
    å¥ij
    0.10
    æĹłè¾ľ
    0.09
    _CALC
    0.09
    äºİæѤ
    0.09
    ä¹ŁåĽłæѤ
    0.09
    çĥŁåĽ±
    0.09
    éļıä¹ĭ
    0.09
    ä¸Ģæłĭ
    0.08
    Activations Density 0.069%

    No Known Activations