© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    ’s, -sn, -to, opera, ful, of, vision, ling, shells, -lag

    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
    åIJĥ饱
    -0.10
     pragma
    -0.09
    çıIJ
    -0.09
    plash
    -0.09
    PropertyParams
    -0.08
    主人åħ¬
    -0.08
    åĽŀåij³
    -0.08
    fers
    -0.08
     sourceMapping
    -0.08
    CppObject
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.11
    ä¸įéĶĻ
    0.09
    bound
    0.09
    apped
    0.09
    assed
    0.08
    ä¸Ģæł·çļĦ
    0.08
    hart
    0.08
    burger
    0.08
    æĪ®
    0.08
    KeyValue
    0.08
    Activations Density 0.077%

    No Known Activations