© 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. 62917
    Prev
    Next
    INDEX
    Explanations

    anxiety

    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
    jid
    -0.09
    unate
    -0.09
    aring
    -0.09
    Ñģ
    -0.09
    åĴĮåľ°åĮº
    -0.09
    leaf
    -0.09
    atab
    -0.08
    PER
    -0.08
    ucc
    -0.08
    æķ´ä½ĵ
    -0.08
    POSITIVE LOGITS
    å·´æĭī
    0.09
    紧迫
    0.09
    onaut
    0.09
    /javascript
    0.09
    ä¸įå·²
    0.09
    çIJ¥
    0.09
    ãĤīãģı
    0.09
    suite
    0.08
    æı¡
    0.08
    ingly
    0.08
    Activations Density 0.004%

    No Known Activations