© 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. 57212
    Prev
    Next
    INDEX
    Explanations

    counts and charges

    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
     Ultimate
    -0.10
    yii
    -0.10
    éºĵ
    -0.09
    éŃĤ
    -0.09
    天æ°Ķ
    -0.08
    ÑħоÑĤ
    -0.08
     opposition
    -0.08
    ä¸įè§ģ
    -0.08
    æĢĢçĸij
    -0.07
    对éĿ¢
    -0.07
    POSITIVE LOGITS
    uple
    0.11
    à¸Ĥà¸Ńà¸ĩà¸ģาร
    0.10
    æĿ¥çĶµ
    0.10
    pson
    0.10
    ä½ľæ¡Ī
    0.09
    æ´²
    0.09
    appen
    0.09
    åĪ¶
    0.09
    InstanceOf
    0.09
    TAIL
    0.09
    Activations Density 0.003%

    No Known Activations