© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9734
    Prev
    Next
    INDEX
    Explanations

    smartphone features and functions

    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
    ãģ®ãģĮ
    -0.10
    ocation
    -0.09
    ÅŁi
    -0.09
    abouts
    -0.09
    aja
    -0.09
    rv
    -0.09
    主任
    -0.09
    ware
    -0.08
    otron
    -0.08
    åħ±å»º
    -0.08
    POSITIVE LOGITS
    ä¸ĢæĹı
    0.13
    ä¸Ģç³»åĪĹ
    0.10
    mons
    0.10
    plied
    0.10
    ucker
    0.10
    мел
    0.09
    fony
    0.09
    tern
    0.09
    çŁ¥è¯ĨåĪĨåŃIJ
    0.09
    ÑĦон
    0.09
    Activations Density 0.010%

    No Known Activations