© 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. 54255
    Prev
    Next
    INDEX
    Explanations

    Rao, Mao, ao names

    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
    ambda
    -0.10
    ee
    -0.09
    åĦ¿
    -0.09
    ly
    -0.09
    e
    -0.08
    mes
    -0.08
    _GRA
    -0.08
    å¥īçĮ®
    -0.08
    ms
    -0.08
    rom
    -0.08
    POSITIVE LOGITS
    istros
    0.10
    otec
    0.10
    ä½łçŁ¥éģĵ
    0.09
    ħ
    0.09
    YOU
    0.09
    ist
    0.09
     Skinny
    0.09
    èĬĴ
    0.09
    ä¸Ģä¸ĸ
    0.09
    дж
    0.08
    Activations Density 0.025%

    No Known Activations