© 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. 2201
    Prev
    Next
    INDEX
    Explanations

    lovely

    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
    æĭ¯
    -0.10
     noqa
    -0.09
    ters
    -0.09
    um
    -0.09
    o
    -0.09
    n
    -0.09
    oub
    -0.08
    å·«
    -0.08
    le
    -0.08
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    POSITIVE LOGITS
    heid
    0.10
    cation
    0.10
    ä¹ĭå¤Ħ
    0.10
    #__
    0.10
    nard
    0.09
    å©¿
    0.09
    å«Ķ
    0.09
    æĦĶ
    0.09
    aggi
    0.09
    grams
    0.09
    Activations Density 0.003%

    No Known Activations