© 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. 62524
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ениÑİ
    -0.09
    é»Ħæĺı
    -0.09
    allon
    -0.08
    ugen
    -0.08
    defgroup
    -0.08
    ks
    -0.08
    æĢł
    -0.08
    çĭ¬
    -0.08
    доÑĢ
    -0.08
    PEAR
    -0.08
    POSITIVE LOGITS
    èħ¹
    0.09
    erer
    0.09
    æ°Ķè¡Ģ
    0.09
    æĮŁ
    0.08
    snow
    0.08
    åģļäºĭ
    0.08
    é²ľ
    0.08
    çĶŁäº§åĬĽ
    0.08
    æľīæĿ¡ä»¶çļĦ
    0.08
    å±Ĥå±Ĥ
    0.08
    Activations Density 0.000%

    No Known Activations