© 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. 48993
    Prev
    Next
    INDEX
    Explanations

    pyramids and pyramidellidae

    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
    ility
    -0.12
    å¼¹æĢ§
    -0.10
    ourn
    -0.09
    çīĮçħ§
    -0.09
    çĶ¨åĵģ
    -0.08
    ements
    -0.08
    æĮİ
    -0.08
    裨
    -0.08
    ifa
    -0.08
    èĶij
    -0.08
    POSITIVE LOGITS
    éĩijåŃĹå¡Ķ
    0.10
    èĪ¬çļĦ
    0.10
    سÙĥ
    0.10
    ä¸Ģå±Ĥ
    0.10
    建æĪIJåIJİ
    0.09
    å·į
    0.09
    ä¸Ģè§Ĵ
    0.09
    å¼ıçļĦ
    0.09
    -shaped
    0.09
    å°ĸ
    0.09
    Activations Density 0.014%

    No Known Activations