© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52329
    Prev
    Next
    INDEX
    Explanations

    removed, from, out, exclude

    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
     Natal
    -0.10
    æ±Ģ
    -0.09
    å®īå®ļ
    -0.09
    ç¼
    -0.09
    éĩĮéĿ¢æľī
    -0.09
    à¸ķะ
    -0.09
    åīįè¿°
    -0.08
    澡
    -0.08
    //================================================================
    -0.08
    è¿ĺæľīä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
     khá»ıi
    0.16
    åİ»äºĨ
    0.11
    æİīäºĨ
    0.10
     removeFrom
    0.09
     from
    0.09
    ç»ķ
    0.09
    à¸Ńà¸Ńà¸ģà¸Īาà¸ģ
    0.09
    .removeFrom
    0.09
    éĻĪè¿°
    0.08
    ROL
    0.08
    Activations Density 0.083%

    No Known Activations