© 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. 4897
    Prev
    Next
    INDEX
    Explanations

    dollars worth of

    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
    éĢIJæŃ¥
    -0.10
    StringEncoding
    -0.09
     hoạch
    -0.09
    çĤ¼
    -0.09
    çĢļ
    -0.09
    Ïĭ
    -0.09
    è¦ĨçĽĸçİĩ
    -0.09
    InstanceState
    -0.09
    éĴ¥åĮĻ
    -0.09
     &___
    -0.08
    POSITIVE LOGITS
     worth
    0.13
    oded
    0.11
    worth
    0.11
    çļĦåķĨåĵģ
    0.10
    aroo
    0.09
    aset
    0.09
    çĵľ
    0.09
    级åĪ«çļĦ
    0.09
    ful
    0.08
    æĿĤ
    0.08
    Activations Density 0.073%

    No Known Activations