© 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. 11293
    Prev
    Next
    INDEX
    Explanations

    video recording capabilities and media

    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
    esco
    -0.09
    haar
    -0.08
    leton
    -0.08
    åĩĨæŶ
    -0.08
     Wheels
    -0.08
    ãģĦãģŁãĤī
    -0.08
    æĬ±åĽ¢
    -0.08
    åģ¾
    -0.08
    ized
    -0.08
    å®ŀä¸ļ
    -0.08
    POSITIVE LOGITS
    å½ķ
    0.13
    å½ķåĥı
    0.11
    éĮĦ
    0.11
     clip
    0.10
     clips
    0.10
    ðŁĵ¹
    0.10
    è§Ĩé¢ij
    0.09
     footage
    0.09
    videos
    0.09
    ä¸Ģæīĭ
    0.09
    Activations Density 0.030%

    No Known Activations