© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19544
    Prev
    Next
    INDEX
    Explanations

    spacious accommodation

    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
    uchen
    -0.10
    arth
    -0.09
    aled
    -0.09
    大ä¼Ĺ
    -0.08
    imb
    -0.08
    icit
    -0.08
    priority
    -0.08
    /GPL
    -0.08
    çī¹æ®ĬæĥħåĨµ
    -0.08
     chance
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    íŀĪ
    0.11
    NESS
    0.10
    æĪ¶
    0.10
    -fw
    0.09
    åľ°è¯´
    0.09
    æĹłæ¯Ķ
    0.09
    ç»Ļ人
    0.09
    èµ·æĿ¥
    0.09
    宽æķŀ
    0.09
    Activations Density 0.005%

    No Known Activations