© 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. 19725
    Prev
    Next
    INDEX
    Explanations

    principle 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
    iet
    -0.09
    ãĤĭãĤĪãģĨãģ«
    -0.08
    TL
    -0.08
    èħ»
    -0.08
     MAS
    -0.08
     référence
    -0.07
     exc
    -0.07
    _aligned
    -0.07
    æľĢå¤ļçļĦ
    -0.07
    بÙĪÙĦ
    -0.07
    POSITIVE LOGITS
    åĴĮæĬĢæľ¯
    0.14
    åİŁåĪĻ
    0.13
    çIJĨ论ä¸Ĭ
    0.12
     principle
    0.11
    åİŁçIJĨ
    0.10
    éĿ¢åŃIJ
    0.10
    å°ıäºĭ
    0.10
     Scal
    0.10
    çļĦåİŁåĪĻ
    0.10
    åİŁåīĩ
    0.10
    Activations Density 0.084%

    No Known Activations