© 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. 5282
    Prev
    Next
    INDEX
    Explanations

    primary care management

    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
    atcher
    -0.11
    æĶ¹æŃ£
    -0.09
    æīģ
    -0.09
    atched
    -0.08
    躺çĿĢ
    -0.08
     batt
    -0.08
    楫
    -0.08
    伶
    -0.08
    çłĶ究æīĢ
    -0.08
     Colo
    -0.08
    POSITIVE LOGITS
     AUTHORS
    0.09
    åīĬå¼±
    0.09
    åѱ
    0.09
    usk
    0.08
    åŁºå±Ĥ
    0.08
    夤
    0.08
    flo
    0.08
     Watson
    0.08
    åij¼åºĶ
    0.08
    çĮĿ
    0.08
    Activations Density 0.501%

    No Known Activations