© 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. 10654
    Prev
    Next
    INDEX
    Explanations

    Scottish Folds

    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
    preg
    -0.09
    æľĶ
    -0.09
    å¡Į
    -0.09
    æĬ¢åħĪ
    -0.09
    ius
    -0.09
    Pocket
    -0.08
    æ¤ħ
    -0.08
    å±ĭ
    -0.08
    åħħçĶµ
    -0.08
    伸
    -0.08
    POSITIVE LOGITS
    ä¸Ģè½®
    0.11
    第ä¸Ģ书记
    0.09
    ç¾İ容
    0.09
    åľ¨å¸Ĥåľºä¸Ĭ
    0.09
    umb
    0.09
    ç¨Ģ
    0.09
    ฮา
    0.09
    æŀ¶
    0.08
    æĺ³
    0.08
     heels
    0.08
    Activations Density 0.142%

    No Known Activations