© 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. 9639
    Prev
    Next
    INDEX
    Explanations

    medication inhibitor

    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
    _GU
    -0.10
    WithIdentifier
    -0.10
    èµ·çłģ
    -0.10
    urai
    -0.09
    æľĢå°ij
    -0.09
    强çĥĪ
    -0.09
    æ·±å¤ľ
    -0.09
    atie
    -0.08
    icina
    -0.08
    å²
    -0.08
    POSITIVE LOGITS
    åīĬ
    0.09
    æŀ¢çº½
    0.09
    .cookies
    0.09
    åŁİå¸Ĥ管çIJĨ
    0.08
     Cycl
    0.08
    æµ£
    0.08
     Bay
    0.08
    éļľ
    0.08
     Runner
    0.08
     impro
    0.08
    Activations Density 0.315%

    No Known Activations