© 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. 36390
    Prev
    Next
    INDEX
    Explanations

    axillary, inguinal, crotch

    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
    åīįçŀ»æĢ§
    -0.10
    ä¸ĢåĪ»
    -0.10
    iti
    -0.09
    ulary
    -0.09
    xED
    -0.09
    çľ¼ç§ij
    -0.08
    ramer
    -0.08
    راÙħ
    -0.08
    entiful
    -0.08
    PropertyParams
    -0.08
    POSITIVE LOGITS
    æĭIJ
    0.10
    èĬĿ
    0.09
    angle
    0.09
     Wilmington
    0.08
     Gus
    0.08
    ripe
    0.08
    æĹ¶æ®µ
    0.08
    æģ½
    0.08
    éŨæĪ·
    0.08
    جا
    0.08
    Activations Density 0.016%

    No Known Activations