© 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. 55592
    Prev
    Next
    INDEX
    Explanations

    easier difficulty

    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
    æı¡
    -0.11
    ä½łåºĶ该
    -0.11
    æĬķèµĦé¢Ŀ
    -0.10
    enberg
    -0.10
    èĻ¬
    -0.10
    .djang
    -0.09
    磼
    -0.09
    ALAR
    -0.09
    cej
    -0.09
    æĶ¾åѦ
    -0.09
    POSITIVE LOGITS
     Sponsored
    0.09
    骨头
    0.08
    æºħ
    0.08
    å¤ĸåªĴ
    0.08
    åľ°æĸ¹æĶ¿åºľ
    0.08
    ibox
    0.08
    owo
    0.07
    åĪį
    0.07
    éĥ½å¾Ī
    0.07
    3
    0.07
    Activations Density 0.101%

    No Known Activations