© 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. 62853
    Prev
    Next
    INDEX
    Explanations

    blood circulation

    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
    åĸī
    -0.10
    urette
    -0.09
    LECTION
    -0.09
    è¾Ī
    -0.09
    è¡į
    -0.08
    throat
    -0.08
    ä¸İæŶ
    -0.08
    Nam
    -0.08
    ä»İä¸Ń
    -0.08
     tant
    -0.08
    POSITIVE LOGITS
    å·¡è§Ĩ
    0.11
    ä¸ĵ项è¡ĮåĬ¨
    0.10
     bloodstream
    0.10
    è·¯è¿ĩ
    0.10
    å·¡
    0.09
    å°ģéĶģ
    0.09
    伸æīĭ
    0.09
    ë§IJ
    0.09
    è§IJ
    0.09
    çī¹æ´¾åijĺ
    0.09
    Activations Density 0.264%

    No Known Activations