© 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. 57568
    Prev
    Next
    INDEX
    Explanations

    anxiety and anxious 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
    饶
    -0.09
    èĨĬ
    -0.09
    平衡
    -0.09
    ç§ijçłĶéĻ¢
    -0.08
    å¾ģæ±Ĥ
    -0.08
    诱人
    -0.08
     unilateral
    -0.08
    ment
    -0.08
    审ç¾İ
    -0.08
     IRC
    -0.08
    POSITIVE LOGITS
    çĦ¦èĻij
    0.14
     anxiety
    0.14
     Anxiety
    0.13
    ä¸įå®ī
    0.11
    æĥ´
    0.11
    ä¸įæķ¢
    0.10
    anship
    0.10
    污æŁĵéĺ²æ²»
    0.10
     anxious
    0.10
    /an
    0.09
    Activations Density 0.071%

    No Known Activations