© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22154
    Prev
    Next
    INDEX
    Explanations

    its affiliates or subsidiary

    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
    ä¸Ģ身
    -0.10
    asher
    -0.09
    åĽĽé¡¹
    -0.09
    åľī
    -0.09
    çIJ¼
    -0.08
    æľ¬æĿ¥å°±
    -0.08
    eced
    -0.08
     Weiner
    -0.08
    ernal
    -0.08
    æĸ°åĬ¨èĥ½
    -0.08
    POSITIVE LOGITS
    缴è¾ĸ
    0.10
    è¡Ķ
    0.10
    åħ¨ä½ĵåijĺå·¥
    0.09
     lam
    0.09
    å·²ç»ıæľī
    0.09
    RSS
    0.09
    éĶIJ
    0.09
    igon
    0.09
    åīįç½®
    0.08
    icont
    0.08
    Activations Density 0.080%

    No Known Activations