© 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. 53901
    Prev
    Next
    INDEX
    Explanations

    a list of

    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
    çIJĨä¼ļ
    -0.09
    æ©Ľ
    -0.08
    éĢģä¸Ĭ
    -0.08
    èĪµ
    -0.08
    å¥ĭæĸĹ缮æłĩ
    -0.08
    å¹ķåIJİ
    -0.08
    æ³ķåѦ
    -0.08
    å±ķåĵģ
    -0.08
    dit
    -0.08
    èIJ½å¹ķ
    -0.08
    POSITIVE LOGITS
    à¹Ħว
    0.10
    åĪĨå¼Ģ
    0.09
    ãĥ¡ãĥ³ãĥĪ
    0.08
    æİĴ
    0.08
    å¼ĢéŨ
    0.08
     Ùģإذا
    0.08
    ujÄħcy
    0.08
    ä¼ī
    0.08
    æľį
    0.08
    .Typed
    0.08
    Activations Density 0.024%

    No Known Activations