© 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. 54658
    Prev
    Next
    INDEX
    Explanations

    tractor locomotion

    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
    клад
    -0.10
    lix
    -0.08
    ä¹ĭä½ľ
    -0.08
    kening
    -0.08
    Ø®ÙĬر
    -0.08
    ry
    -0.08
    çģ
    -0.08
    iggins
    -0.08
    night
    -0.08
    abcdef
    -0.08
    POSITIVE LOGITS
    èĭ´
    0.10
    /OR
    0.10
    夫
    0.10
    eur
    0.10
    å¬ĸ
    0.09
    swith
    0.09
    ä¸Ģ线
    0.09
    ISTS
    0.08
    æľĭ
    0.08
     Brewing
    0.08
    Activations Density 0.006%

    No Known Activations