© 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. 26454
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in -like

    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
    lands
    -0.10
    land
    -0.09
    naire
    -0.09
    åģľä¸ĭæĿ¥
    -0.09
    æĹ¶ä»£çļĦ
    -0.09
    æ´¾
    -0.09
    -era
    -0.09
    å¾Īéķ¿æŶéĹ´
    -0.08
     klein
    -0.08
    æĺī
    -0.08
    POSITIVE LOGITS
    éļ½
    0.10
     qualities
    0.09
    ugas
    0.09
    æľĪç»ı
    0.09
    çķ¶çĦ¶
    0.09
    sus
    0.08
    çŃ¾
    0.08
    inery
    0.08
    hev
    0.08
    ä¸ĢèĦļ
    0.08
    Activations Density 0.016%

    No Known Activations