© 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. 22462
    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
    æľī两ç§į
    -0.09
    溢
    -0.09
    æħij
    -0.08
    综åIJĪç´łè´¨
    -0.08
    çĽ¼
    -0.08
    annt
    -0.08
    rob
    -0.08
    ange
    -0.08
    ç½®
    -0.08
     Zy
    -0.08
    POSITIVE LOGITS
    åİŁåĪĻ
    0.26
    çļĦåİŁåĪĻ
    0.22
     principle
    0.21
    åŁºæľ¬åİŁåĪĻ
    0.20
    åİŁåīĩ
    0.20
     principles
    0.19
     Principle
    0.18
     пÑĢинÑĨип
    0.17
     principio
    0.16
     Principles
    0.16
    Activations Density 0.123%

    No Known Activations