© 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. 57546
    Prev
    Next
    INDEX
    Explanations

    number one

    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
    æ¯įåħ¬åı¸
    -0.08
    esh
    -0.08
    utton
    -0.08
    çºł
    -0.08
    çıª
    -0.08
    æĤł
    -0.08
    -HT
    -0.08
    /cms
    -0.08
    vertiser
    -0.08
    .ut
    -0.08
    POSITIVE LOGITS
    eer
    0.09
     thing
    0.09
    åģļçļĦäºĭ
    0.09
    ê°ĢëĬĶ
    0.09
    -selling
    0.09
    -rated
    0.09
    æ·Ĩ
    0.09
    THING
    0.09
    å½ĵçĦ¶æĺ¯
    0.08
    çİĭèĢħ
    0.08
    Activations Density 0.011%

    No Known Activations