© 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. 35566
    Prev
    Next
    INDEX
    Explanations

    unsuspecting, innocent, unexpected

    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
    åı¯æĥľ
    -0.10
    åIJĦè¡Į
    -0.10
    åĨ³ä¸į
    -0.10
    åĽ½å®ī
    -0.10
    èķĪ
    -0.09
    鹤
    -0.08
    çªĸ
    -0.08
    æľīä¸ĢçĤ¹
    -0.08
    lectic
    -0.08
    å¹»æĥ³
    -0.08
    POSITIVE LOGITS
     unsus
    0.10
    èĢ³æľµ
    0.09
     ×Ķר
    0.08
    å«Įçĸij
    0.08
    æľĽåİ»
    0.08
    家ä¼ģä¸ļ
    0.08
    éĸĵãģ«
    0.08
    å¢ĻéĿ¢
    0.08
    eware
    0.08
    ajo
    0.08
    Activations Density 0.016%

    No Known Activations