© 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. 48240
    Prev
    Next
    INDEX
    Explanations

    sentenced to probation or appearances

    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
    åĪĩæį¢
    -0.09
    æĪĸå¤ļ
    -0.09
    beck
    -0.08
    .oper
    -0.08
    ä¹ħ
    -0.08
    amma
    -0.08
    ç³Ļ
    -0.08
    asaki
    -0.08
     tro
    -0.08
    pyx
    -0.08
    POSITIVE LOGITS
    æľŁåĨħ
    0.09
    otron
    0.09
    åIJĪ
    0.09
    åħ¬çĽĬ
    0.09
    å¯ĵæĦı
    0.09
    ernet
    0.09
    æŁ¥çľĭ详æĥħ
    0.09
    çŃīå¤ļ项
    0.09
    æݨèįIJéĺħ读
    0.09
    天使
    0.09
    Activations Density 0.034%

    No Known Activations