© 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. 32655
    Prev
    Next
    INDEX
    Explanations

    thyroid disorders and iodine

    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
    strup
    -0.10
    å°¾
    -0.09
    èħ°
    -0.09
    褥
    -0.09
    æı©
    -0.09
    STANCE
    -0.09
    è·Į
    -0.09
    ubb
    -0.09
    angel
    -0.08
    usb
    -0.08
    POSITIVE LOGITS
    çĶ²çĬ¶èħº
    0.11
    å´¤
    0.11
    åŀĤ
    0.10
    ç¡Ĵ
    0.10
    çļĦé£Łçī©
    0.10
    æ´Ļ
    0.09
    åĨ¶çĤ¼
    0.09
    çłľ
    0.09
    RIA
    0.09
    æ·Ħ
    0.09
    Activations Density 0.176%

    No Known Activations