© 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. 58386
    Prev
    Next
    INDEX
    Explanations

    t0mas

    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
    纽带
    -0.09
    å´Ľ
    -0.09
    ä¸įå®Į
    -0.09
    éĴ²
    -0.09
     Fin
    -0.09
    iant
    -0.09
    产ä¸ļåıijå±ķ
    -0.08
     Craw
    -0.08
     Chand
    -0.08
    ä¼ĺéĽħ
    -0.08
    POSITIVE LOGITS
    LP
    0.09
    oley
    0.09
    esters
    0.09
    _MIX
    0.09
    lp
    0.09
    gether
    0.09
    ç½²
    0.08
    æµ®
    0.08
    alty
    0.08
    ever
    0.08
    Activations Density 0.251%

    No Known Activations