© 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. 39492
    Prev
    Next
    INDEX
    Explanations

    paracrine and endocrine functions

    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
    -tm
    -0.10
    зо
    -0.09
    è¯Ī
    -0.09
    quot
    -0.09
    iliation
    -0.09
    çIJĨ解åĴĮ
    -0.08
    çļĦç¨ĭ度
    -0.08
    åIJīåĪ©
    -0.08
    ä¸Ģäºĭ
    -0.08
    æĿµ
    -0.08
    POSITIVE LOGITS
    æľīèī²
    0.11
    åĮĿ
    0.10
    ä¿¡åı·
    0.09
    pane
    0.08
     signals
    0.08
    æ²Ń
    0.08
    è¯ķé¢ĺ
    0.08
     pró
    0.08
    æĻ¯å¾·éķĩ
    0.08
    .transform
    0.08
    Activations Density 0.697%

    No Known Activations