© 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. 61437
    Prev
    Next
    INDEX
    Explanations

    is followed by verbs indicating state or change

    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
    å¹²éĥ¨
    -0.10
    éĴ¢
    -0.10
    èĤ¡ä»·
    -0.09
    ifr
    -0.09
    hta
    -0.09
    æĹ¥åŃIJ
    -0.09
    å§Ĩ
    -0.09
    zelf
    -0.09
    cope
    -0.09
    ModelError
    -0.09
    POSITIVE LOGITS
    èĵ¬åĭĥåıijå±ķ
    0.11
    é«ĺéĢŁåıijå±ķ
    0.09
    åģ¥åº·åıijå±ķ
    0.09
    åIJij举
    0.08
    cr
    0.08
    快讯
    0.07
     itself
    0.07
    ripper
    0.07
     kali
    0.07
    rite
    0.07
    Activations Density 0.259%

    No Known Activations