© 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. 2258
    Prev
    Next
    INDEX
    Explanations

    providing enough or sufficient

    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
    ä¸įç»ı
    -0.10
    _cid
    -0.10
    éĿ
    -0.09
    ä¸ĩéĩĮ
    -0.09
    CID
    -0.08
    afe
    -0.08
    éĽķ
    -0.08
    åįģæĿ¡
    -0.08
    _PO
    -0.08
    cid
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.19
     долж
    0.16
    åħħåĪĨ
    0.15
    åºĶæľīçļĦ
    0.14
     enough
    0.14
    è¶³å¤Ł
    0.14
    æľīè¶³å¤ŁçļĦ
    0.13
     sufficient
    0.12
     ×ŀספ×Ļק
    0.12
     доÑģÑĤаÑĤ
    0.12
    Activations Density 0.134%

    No Known Activations