© 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. 62454
    Prev
    Next
    INDEX
    Explanations

    lawsuit

    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
    cie
    -0.09
    ORY
    -0.09
     lique
    -0.09
    اة
    -0.09
    InitialState
    -0.09
     tâm
    -0.08
    æĬķæľº
    -0.08
    dae
    -0.08
    wayne
    -0.08
    ç»ıçIJĨ
    -0.08
    POSITIVE LOGITS
     demás
    0.09
    IGNAL
    0.09
    éĴĹ
    0.09
    æľīåĪ©
    0.09
    ä¸ĥåħ«
    0.09
    ities
    0.08
    ears
    0.08
    ugg
    0.08
    utable
    0.08
    åĴĮåľ°åĮº
    0.08
    Activations Density 0.007%

    No Known Activations