© 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. 55649
    Prev
    Next
    INDEX
    Explanations

    data communication services

    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
    æļĹæļĹ
    -0.10
    寨
    -0.09
    çĭIJ
    -0.09
    æĿ¥è®²
    -0.09
    achs
    -0.09
    çĶµè§Ĩ
    -0.09
    æīİ
    -0.08
    duino
    -0.08
    æIJ¦
    -0.08
    affer
    -0.08
    POSITIVE LOGITS
    æ³ī
    0.11
     Glover
    0.09
    irs
    0.09
    å¥ij
    0.08
    æ¡£
    0.08
    TestData
    0.08
    å¥ij约
    0.08
    elib
    0.08
    æłĹ
    0.08
    rir
    0.08
    Activations Density 0.173%

    No Known Activations