© 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. 10058
    Prev
    Next
    INDEX
    Explanations

    played in

    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
    ä¸Ģ个个
    -0.09
    è´¯éĢļ
    -0.08
    \Eloquent
    -0.08
     Hind
    -0.08
    ä»°
    -0.08
    çĸijéļ¾
    -0.08
    天ä¸ĭ
    -0.08
    owment
    -0.08
    ipl
    -0.08
    马åĬĽ
    -0.08
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.11
     Successfully
    0.10
     successfully
    0.10
    Successfully
    0.10
    æĪIJåĬŁçļĦ
    0.10
    顺åĪ©å®ĮæĪIJ
    0.09
    åĩºèī²
    0.09
    eri
    0.09
     successful
    0.09
    åĬłåĢį
    0.09
    Activations Density 0.061%

    No Known Activations