© 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. 48415
    Prev
    Next
    INDEX
    Explanations

    operating system

    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
    åĮĹ大
    -0.10
    å·¥ä½ľç»ıéªĮ
    -0.10
    à¹Ĩ
    -0.09
    åŃIJéĩĮ
    -0.09
    à¸ĺรรม
    -0.09
     à¹Ĩ
    -0.09
    rising
    -0.08
    alysis
    -0.08
    ish
    -0.08
    ort
    -0.08
    POSITIVE LOGITS
    inia
    0.09
    ERO
    0.09
    æĹ¥è®¯
    0.09
    ipple
    0.09
    (OS
    0.09
    ×Ĵ×Ļ׾
    0.09
    rompt
    0.09
    ainter
    0.08
    èĢħçļĦ
    0.08
    ADOR
    0.08
    Activations Density 0.011%

    No Known Activations