© 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. 56018
    Prev
    Next
    INDEX
    Explanations

    residency program or fellow scholar

    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
    getConfig
    -0.09
    allel
    -0.09
    åĶ¤éĨĴ
    -0.09
    ç»ıè¿ĩå¤ļå¹´
    -0.08
    æij¸
    -0.08
    lyn
    -0.08
    åħĭæľį
    -0.08
    áĢĬ
    -0.08
    ziel
    -0.08
    æ·±å±Ĥ次
    -0.08
    POSITIVE LOGITS
     residency
    0.11
    é©»æĿij
    0.11
    访éĹ®
    0.11
    訪
    0.11
    åĢ¼å®Ī
    0.10
    è¿Ľé©»
    0.10
    åħ¥ä½ı
    0.10
     incub
    0.10
    访
    0.10
    é©»
    0.10
    Activations Density 0.082%

    No Known Activations