© 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. 58863
    Prev
    Next
    INDEX
    Explanations

    mediocre or special

    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
    è¶ĬæĿ¥è¶Ĭå°ij
    -0.09
    lico
    -0.08
    _BAR
    -0.08
    -bar
    -0.08
    ibur
    -0.08
    äº¤æĽ¿
    -0.08
    _SLAVE
    -0.08
    æŃª
    -0.08
    eneg
    -0.08
    anky
    -0.08
    POSITIVE LOGITS
    平淡
    0.18
    å¹³åĩ¡
    0.16
    ä¹Łæ²¡ä»Ģä¹Ī
    0.15
    æĻ®éĢļçļĦ
    0.15
    没æľīä»Ģä¹Ī
    0.14
    没ä»Ģä¹Ī
    0.14
    没åķ¥
    0.13
    æĻ®éĢļ
    0.13
    èĬ¸
    0.13
    åĩºä¼Ĺ
    0.12
    Activations Density 0.067%

    No Known Activations