© 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. 17749
    Prev
    Next
    INDEX
    Explanations

    thyroid conditions and disorders

    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
    éģķãģĦ
    -0.09
    ÙĪز
    -0.09
    VICE
    -0.09
     unins
    -0.08
    sterol
    -0.08
    ì§Ŀ
    -0.08
    æŃĨ
    -0.08
     ÑĤебе
    -0.08
    INED
    -0.08
    Denied
    -0.08
    POSITIVE LOGITS
    ãģ¶ãĤĬ
    0.09
    ening
    0.09
    idades
    0.09
    ened
    0.08
    çĹĩ
    0.08
    esser
    0.08
    ism
    0.08
    å¹´é¾Ħ段
    0.08
    å¤Ħæĸ¹
    0.08
    ç¢į
    0.08
    Activations Density 0.113%

    No Known Activations