© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38292
    Prev
    Next
    INDEX
    Explanations

    numbers followed by k or comma

    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
    çĶµå·¥
    -0.09
    è°
    -0.09
    erne
    -0.09
    æĪ¿æºIJ
    -0.08
    _Ptr
    -0.08
    çı©
    -0.08
    éĻķ西
    -0.08
    пÑĥÑģк
    -0.08
    пÑĥÑī
    -0.08
    ingles
    -0.08
    POSITIVE LOGITS
    äºĤ
    0.10
    å¾Ĺèµ·
    0.09
    ä¹±
    0.08
    илÑģÑı
    0.08
    å¢ĥ
    0.08
    æĻ¦
    0.08
    å¼ĥ
    0.08
    Knife
    0.08
    éĨį
    0.08
     per
    0.08
    Activations Density 0.061%

    No Known Activations