© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35817
    Prev
    Next
    INDEX
    Explanations

    dental and clinical

    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
    èĵį
    -0.11
    åķ¬
    -0.10
    åŃ£
    -0.09
    å·¥ç¨ĭ建设
    -0.09
    çħ¤æ°Ķ
    -0.08
    ä¸ĬåѦ
    -0.08
    å®Ĺ
    -0.08
    é«ĺ空
    -0.08
    ainment
    -0.08
     Nimbus
    -0.08
    POSITIVE LOGITS
    é¾Ī
    0.14
    é¾ĭ
    0.13
    åı£èħĶ
    0.12
     dentist
    0.12
    odont
    0.12
    çīĻ
    0.12
     dental
    0.11
     Dental
    0.11
    çīĻ齿
    0.11
    齿
    0.11
    Activations Density 0.485%

    No Known Activations