© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22270
    Prev
    Next
    INDEX
    Explanations

    connective tissue

    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
    ABEL
    -0.09
    ëī´ìĬ¤
    -0.09
    è¾ĺ
    -0.09
    è¿ĪåIJij
    -0.09
    æ¸ł
    -0.09
    è§īå¾Ĺèĩªå·±
    -0.08
    æĮĤçīĮ
    -0.08
    便
    -0.08
     Sad
    -0.08
    æľīåĩłä¸ª
    -0.08
    POSITIVE LOGITS
    çŃĭ
    0.11
    æŁĶ软
    0.10
     tissue
    0.10
    ç»Ħç»ĩ
    0.10
     mus
    0.09
     connect
    0.09
    软
    0.09
    纽带
    0.09
    .struct
    0.09
    æŁĶ
    0.09
    Activations Density 0.226%

    No Known Activations