© 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. 47770
    Prev
    Next
    INDEX
    Explanations

    keyboard and mouse controls

    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
     Slee
    -0.10
    åĪ»
    -0.10
    plash
    -0.08
    çĴĭ
    -0.08
    åħīçݯ
    -0.08
    hou
    -0.08
    ä¸Ģæĸ¹
    -0.08
    inary
    -0.08
    esco
    -0.08
    æĴ¬
    -0.08
    POSITIVE LOGITS
    çķı
    0.10
    伫
    0.10
    秽
    0.10
    çļĦæĵįä½ľ
    0.10
    è¡ĮåĬ¨
    0.09
    建çŃijå·¥ç¨ĭ
    0.09
    çłĤ
    0.09
    èĤī
    0.09
    _INLINE
    0.09
    åij½ä»¤
    0.09
    Activations Density 0.126%

    No Known Activations