© 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. 56686
    Prev
    Next
    INDEX
    Explanations

    series titles

    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
    .lab
    -0.10
    lus
    -0.09
    åİī
    -0.09
    éļı
    -0.09
    ä¸įèµ·
    -0.09
    ä¸įæĸŃåľ°
    -0.08
    å¤ļå¹´çļĦ
    -0.08
    æĬ«
    -0.08
    Ù
    -0.08
    _patterns
    -0.08
    POSITIVE LOGITS
    ches
    0.09
    çļĦ人éĥ½
    0.09
    çĶ¨æ°´
    0.08
    atical
    0.08
    éĴĪ对
    0.08
    俾
    0.08
    åĬŁè¯¾
    0.08
     докÑĥменÑĤов
    0.08
    æĬ¥å¤į
    0.08
    èĢĥå¯Ł
    0.08
    Activations Density 0.028%

    No Known Activations