© 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. 4147
    Prev
    Next
    INDEX
    Explanations

    satire, parody, spoof

    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
     vic
    -0.09
    åĦ¿å¥³
    -0.09
    oming
    -0.09
    æĢĢçĿĢ
    -0.08
    æĸ°çļĦä¸Ģ
    -0.08
    rå
    -0.08
    龸
    -0.08
    anel
    -0.08
    æĻĴ
    -0.08
    æµ·åºķ
    -0.08
    POSITIVE LOGITS
    ues
    0.09
    /mock
    0.09
    ISTIC
    0.09
    ç»Ħç»ĩçĶŁæ´»
    0.09
    ute
    0.09
    奢
    0.09
    èµĸ以çĶŁåŃĺ
    0.09
    itical
    0.09
    漫çĶ»
    0.08
    è°ģèĥ½
    0.08
    Activations Density 0.008%

    No Known Activations