© 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. 34905
    Prev
    Next
    INDEX
    Explanations

    and all / and every / and simple

    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
    åħ¶æ¬¡æĺ¯
    -0.10
    åıŃ
    -0.10
    inne
    -0.10
    åĵªæĢķæĺ¯
    -0.09
    æĿŀ
    -0.09
    åįİå¤ı
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    éĹ»
    -0.09
    çīĿ
    -0.09
    社ä¼ļ责任
    -0.09
    POSITIVE LOGITS
    çīĪæĿĥå½Ĵ
    0.09
    ean
    0.08
    ragen
    0.08
    ä»ħ代表
    0.08
    æµ·åı£
    0.08
    æĪIJæľ¬
    0.08
     вÑģÑı
    0.07
     Represent
    0.07
    jec
    0.07
    rag
    0.07
    Activations Density 0.046%

    No Known Activations