© 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. 50013
    Prev
    Next
    INDEX
    Explanations

    release or discharge from custody

    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
     забол
    -0.09
    ä¸ĢèĤ¡
    -0.09
    çĥ¨
    -0.09
    æĵİ
    -0.09
    å¢Ģ
    -0.09
    åIJĪä¸Ģ
    -0.09
    åħ¥åĽ´
    -0.09
    åĨħ涵
    -0.08
    æĢ§çļĦ
    -0.08
    keit
    -0.08
    POSITIVE LOGITS
    oded
    0.10
    å½Ĵ
    0.10
    constitution
    0.10
    arian
    0.09
     khá»ıi
    0.09
    æѸ
    0.09
    ev
    0.08
    Army
    0.08
    ople
    0.08
    -preview
    0.08
    Activations Density 0.021%

    No Known Activations