© 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. 30984
    Prev
    Next
    INDEX
    Explanations

    meningitis or meningioma

    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
    åĽ½ä¼ļ
    -0.09
    好å¤ļ
    -0.09
    éĺ²çĽĹ
    -0.09
    anke
    -0.09
    ä¸ºæł¸å¿ĥ
    -0.09
     Bauer
    -0.08
    丽
    -0.08
     thoát
    -0.08
    9
    -0.08
     Lands
    -0.08
    POSITIVE LOGITS
     мÑĥ
    0.10
    å±
    0.09
    lam
    0.09
    åŃ¢
    0.09
    ductory
    0.09
    å¾Ĺä¸įåĪ°
    0.09
    æ·ħ
    0.09
    oria
    0.08
    WithValue
    0.08
    VERSION
    0.08
    Activations Density 0.144%

    No Known Activations