© 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. 23436
    Prev
    Next
    INDEX
    Explanations

    use to perform actions

    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
    å¼ŁåŃIJ
    -0.08
    ä¾ĭãģĪãģ°
    -0.08
    Assignable
    -0.07
    Speak
    -0.07
    :
    -0.07
    派驻
    -0.07
    æī«çłģ
    -0.07
     ÑĢеб
    -0.07
    æݨéĢģ
    -0.07
    严
    -0.07
    POSITIVE LOGITS
    _Component
    0.10
    ä¸įå®Į
    0.10
    åħ¸åŀĭçļĦ
    0.09
    uthor
    0.09
    éĨĭ
    0.09
    ä»ĸæĺ¯ä¸Ģ个
    0.09
    LEE
    0.09
    æĺ¯ä¸Ģ家
    0.09
    å¥ĭæĪĺ
    0.09
    å´§
    0.09
    Activations Density 0.192%

    No Known Activations