© 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. 61114
    Prev
    Next
    INDEX
    Explanations

    even followed by a verb or noun

    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
    è¦ģä¹Ī
    -0.12
    èĻ½çĦ¶
    -0.10
    ä¹ĭåŁİ
    -0.10
    è¾Ħ
    -0.09
    å¦Ĥæŀľä¸į
    -0.09
    åIJĮæĹ¶ä¹Ł
    -0.09
    çļĦåIJĦç§į
    -0.09
    éĽĸçĦ¶
    -0.09
    ä¹Łæľīå¾Īå¤ļ
    -0.09
    ä¹Łè®¸
    -0.09
    POSITIVE LOGITS
    åı¯ä»¥è¯´æĺ¯
    0.09
    ement
    0.09
    çİ©
    0.08
    verständlich
    0.08
    pets
    0.08
    ONES
    0.08
    åĪ»
    0.08
    ä¹İ
    0.08
    衽
    0.08
    æĺ¯ä¸Ģéĥ¨
    0.08
    Activations Density 0.032%

    No Known Activations