© 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. 23183
    Prev
    Next
    INDEX
    Explanations

    javascript and html code

    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
    éĻIJãĤĬ
    -0.10
    æį·
    -0.09
     Lis
    -0.09
    éĴ®
    -0.09
    rop
    -0.08
    yet
    -0.08
    åıĪèĥ½
    -0.08
    ropol
    -0.08
    /sdk
    -0.08
     Kil
    -0.08
    POSITIVE LOGITS
    èĪģ
    0.10
    ÑĪка
    0.10
    åľ¨éĩĮéĿ¢
    0.09
    å°ij许
    0.09
    -speaking
    0.09
    Bins
    0.09
    å¦Ĥä¸ĭ
    0.09
    ä¸Ģæīĭ
    0.09
    æĻ¦
    0.09
    çĦ
    0.08
    Activations Density 0.516%

    No Known Activations