© 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. 23910
    Prev
    Next
    INDEX
    Explanations

    viable option

    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
    ation
    -0.11
    dr
    -0.09
    neath
    -0.09
    halb
    -0.08
    ered
    -0.08
     âľĵ
    -0.08
    eming
    -0.08
    ÑĢаг
    -0.08
     Harr
    -0.08
    íŀĪ
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.09
    æľŁåĨħ
    0.09
    -looking
    0.09
    éħį
    0.09
    á»ĩt
    0.09
    å·²ä¹ħ
    0.09
    ãĥ£
    0.09
    retval
    0.09
    ugin
    0.09
    OptionsMenu
    0.09
    Activations Density 0.006%

    No Known Activations