© 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. 56529
    Prev
    Next
    INDEX
    Explanations

    of all

    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
    æģ¯
    -0.10
    _CNTL
    -0.09
    åŃĹåı·
    -0.08
    ãģĶ覧
    -0.08
    åİļ
    -0.08
    âĪ
    -0.08
    è§Ī
    -0.08
     Meta
    -0.08
    æĪĸå¤ļæĪĸå°ij
    -0.08
    ish
    -0.08
    POSITIVE LOGITS
     вÑģеÑħ
    0.13
    æīĢæľī
    0.12
     ÑģÑĢеди
    0.10
    æīĢæľī人
    0.10
    å¹²èĦĨ
    0.09
    è¿Ļä¸ĢåĪĩ
    0.09
    æĸ°çļĦä¸Ģ
    0.09
    两èĢħ
    0.09
     جÙħÙĬع
    0.09
    sted
    0.09
    Activations Density 0.067%

    No Known Activations