© 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. 49963
    Prev
    Next
    INDEX
    Explanations

    medication and usage

    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
    å¹³åİŁ
    -0.10
    å²Ľå±¿
    -0.09
    è¦Ĩ
    -0.09
    éĥ¨åĪĨåľ°åĮº
    -0.09
    typings
    -0.09
    ä»ģ
    -0.09
    éĥ
    -0.08
     Hamp
    -0.08
    éĢļé£İ
    -0.08
    éĥİ
    -0.08
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯
    0.12
    å°¤åħ¶æĺ¯
    0.12
    æľīä»»ä½ķ
    0.10
    èĨĤ
    0.09
    è¿ijæľŁ
    0.09
    ä¸ĵ享
    0.09
    çģ°
    0.09
    èį¯æĿIJ
    0.09
    åįī
    0.08
    çľģéĴ±
    0.08
    Activations Density 0.016%

    No Known Activations