© 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. 33068
    Prev
    Next
    INDEX
    Explanations

    weight loss and related medical terms

    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
    apel
    -0.10
    大家ä¸Ģèµ·
    -0.09
    uar
    -0.09
    kw
    -0.08
    habi
    -0.08
    ç¥Ŀ
    -0.08
    åĶ¯ç¾İ
    -0.08
    çİĩè¾¾åĪ°
    -0.08
    ç»Ļ人
    -0.08
    _Success
    -0.08
    POSITIVE LOGITS
    æ¦Ľ
    0.10
    家å±ħ
    0.09
    ewise
    0.09
    æµ®åĬ¨
    0.09
    erts
    0.09
    _png
    0.09
    å¹´åīį
    0.08
    å¤ĩ
    0.08
    èĭ¦èĭ¦
    0.08
    èŀįåĮĸ
    0.08
    Activations Density 0.011%

    No Known Activations