© 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. 61439
    Prev
    Next
    INDEX
    Explanations

    settle for, settle in, settle down

    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
    sWith
    -0.12
    /Graphics
    -0.09
    ye
    -0.08
    次ä¼ļè®®
    -0.08
    éħ·
    -0.08
    icc
    -0.08
    ä¸ĩéĩĮ
    -0.08
    å·´æĭī
    -0.08
    _reporting
    -0.08
    ass
    -0.08
    POSITIVE LOGITS
    IZER
    0.09
    纷
    0.09
    çĦ¶æĺ¯
    0.09
    è¿Ļ个éĹ®é¢ĺ
    0.09
    ä¸ĭæĿ¥
    0.09
    idge
    0.09
    ä¸ĭä¾Ĩ
    0.09
    常å§Ķ
    0.09
    ARY
    0.09
    izr
    0.09
    Activations Density 0.006%

    No Known Activations