© 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. 53965
    Prev
    Next
    INDEX
    Explanations

    just right

    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
     Kavanaugh
    -0.11
    æĬ±çĿĢ
    -0.11
    ä¸įéĻIJ
    -0.10
    çĸıéĢļ
    -0.10
    å¹ħ
    -0.09
    iful
    -0.09
    /licenses
    -0.09
    åĴĮæĬĢæľ¯
    -0.09
    çĤ¹äºĨ
    -0.09
    ĥģ
    -0.09
    POSITIVE LOGITS
    çī¹åĪ«
    0.10
    æĭ¿
    0.08
     habitual
    0.08
    çĭ¬çī¹
    0.08
     fint
    0.07
     certain
    0.07
    U
    0.07
    æŁIJç§į
    0.07
    åIJĪéĢĤ
    0.07
     way
    0.07
    Activations Density 0.049%

    No Known Activations