© 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. 51505
    Prev
    Next
    INDEX
    Explanations

    words ending in -ness, -ery, -hem

    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
    èµĦæºIJæķ´åIJĪ
    -0.09
    æk
    -0.09
    uces
    -0.09
    èĩ¨
    -0.09
    ä¸įåĪ°ä½į
    -0.09
    erland
    -0.09
     Trot
    -0.09
    éŁª
    -0.09
    rts
    -0.09
    alach
    -0.09
    POSITIVE LOGITS
    è¿IJèIJ¥ç®¡çIJĨ
    0.11
    ears
    0.10
    mere
    0.09
    kan
    0.09
    椽
    0.09
    ï¸ı
    0.09
    ematic
    0.09
    ubi
    0.08
    ous
    0.08
    ness
    0.08
    Activations Density 0.002%

    No Known Activations