© 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. 31429
    Prev
    Next
    INDEX
    Explanations

    biological fluids

    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
    åĪ¶
    -0.09
    achi
    -0.09
    åijµ
    -0.09
    åĽŀæĥ³
    -0.09
    åIJĮçŃī
    -0.08
    çħ³
    -0.08
    lus
    -0.08
    ÙĬت
    -0.08
    ç¾ļ
    -0.08
    spe
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.15
    æ¯Ķå¦Ĥ
    0.12
    åĮħæĭ¬
    0.12
     including
    0.10
    ä¾ĭå¦Ĥ
    0.09
    including
    0.09
    ä¾ĭãģĪãģ°
    0.09
     ÙĥاÙĦ
    0.09
    IVES
    0.09
    è°¤
    0.09
    Activations Density 0.935%

    No Known Activations