© 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. 57288
    Prev
    Next
    INDEX
    Explanations

    the + abstract nouns

    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
    _utilities
    -0.09
    anga
    -0.09
    обÑĭ
    -0.08
    èĢĮè¨Ģ
    -0.08
    [".
    -0.08
    ieux
    -0.08
    æľĢæľī
    -0.08
    è¿Ļæĺ¯ä¸Ģç§į
    -0.08
    åģļä¸įåĪ°
    -0.07
    alic
    -0.07
    POSITIVE LOGITS
     eventual
    0.10
    æ·Į
    0.10
     ability
    0.10
     inability
    0.09
     possibility
    0.09
     willingness
    0.09
     consequ
    0.09
     chance
    0.09
    éļıä¹ĭ
    0.09
     Möglichkeit
    0.09
    Activations Density 0.126%

    No Known Activations