© 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. 53834
    Prev
    Next
    INDEX
    Explanations

    would/might/if/when

    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
    æĦķ
    -0.10
    æĿĵ
    -0.08
     обÑĭ
    -0.08
    並ä¸Ķ
    -0.08
    èĢĢ
    -0.08
    é¢ľ
    -0.08
    unity
    -0.08
    åĵĹ
    -0.08
    æĭ¿åĩº
    -0.07
    åĩłä¹İæīĢæľī
    -0.07
    POSITIVE LOGITS
    èĻļæŀĦ
    0.10
    åıģ
    0.09
    pes
    0.09
    çĸĨ
    0.09
    æĶ¶åĪ°
    0.08
    æĪIJç«ĭ以æĿ¥
    0.08
    å¹ħ
    0.08
    çīĪæĿĥæīĢæľī
    0.08
     Lal
    0.08
     Covered
    0.08
    Activations Density 0.179%

    No Known Activations