© 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. 9745
    Prev
    Next
    INDEX
    Explanations

    high praise adjectives

    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
    è´±
    -0.10
     tus
    -0.09
    çļĦéĤ£ç§į
    -0.09
    ä¸ĩä¸Ģ
    -0.09
    éĢıè§Ĩ
    -0.09
    Bush
    -0.08
    èĥĸåŃIJ
    -0.08
    ->__
    -0.08
    regs
    -0.08
    gain
    -0.08
    POSITIVE LOGITS
    éĢIJ
    0.10
    èİ«
    0.09
    åİĭåĪ¶
    0.09
    åīįçŀ»
    0.09
    iale
    0.09
    æĹ¶è¾°
    0.09
    åįĵè¶Ĭ
    0.09
    cri
    0.08
    é£İåħī
    0.08
    éĢIJä¸Ģ
    0.08
    Activations Density 0.029%

    No Known Activations