© 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. 37618
    Prev
    Next
    INDEX
    Explanations

    philosophy and cognitive science

    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
    ä»»æĢ§
    -0.10
    éĢļæĬ¥
    -0.10
    çĦĻ
    -0.09
    obl
    -0.09
    æ³ķå®ĺ
    -0.08
    à¸Ħà¸ĩ
    -0.08
    kee
    -0.08
    _choices
    -0.08
    aes
    -0.08
    åı¹
    -0.08
    POSITIVE LOGITS
    ä¸įçŁ¥
    0.09
    ç²¾å¯Ĩ
    0.09
    ç³»
    0.09
     Williamson
    0.09
    æĢĢ念
    0.08
    erve
    0.08
    è¿ijäºĽå¹´
    0.08
    æĤĦçĦ¶
    0.08
    _SPELL
    0.08
    èĬ¬
    0.08
    Activations Density 0.041%

    No Known Activations