© 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. 48695
    Prev
    Next
    INDEX
    Explanations

    shear stress

    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
    kol
    -0.09
     Verde
    -0.08
    åĭĥåĭĥ
    -0.08
    ä»ĺè´¹
    -0.08
     rid
    -0.08
    grav
    -0.08
    å§Ķä¼ļ
    -0.08
    kok
    -0.08
    å¼ķãģį
    -0.08
    itation
    -0.07
    POSITIVE LOGITS
    ppard
    0.10
    æİī
    0.10
    åľ°å¸¦
    0.10
    å¼Ģ
    0.10
    é©·
    0.09
    åŃIJå¼Ł
    0.09
    loom
    0.09
    à¹Į
    0.09
    åħļé£İ
    0.09
    fax
    0.09
    Activations Density 0.015%

    No Known Activations