© 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. 49504
    Prev
    Next
    INDEX
    Explanations

    Girl's awards or appearances

    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
    åĭ°
    -0.09
    ç¥Ĺ
    -0.09
    è¾ij
    -0.09
    æľīçĶ¨çļĦ
    -0.09
     Peters
    -0.09
    kills
    -0.08
    ãģ£ãģ
    -0.08
    ÑĢабоÑĤ
    -0.08
    åĤ¬
    -0.08
    æĬĹè®®
    -0.08
    POSITIVE LOGITS
    SEN
    0.09
    å®Ľ
    0.09
    èĥĮä¸Ĭ
    0.09
    åijľ
    0.08
    æłĿ
    0.08
    äºŃ
    0.08
    æ®Ĭ
    0.08
    æ»´æ»´
    0.08
    éĦĻ
    0.08
    pos
    0.08
    Activations Density 0.004%

    No Known Activations