© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8472
    Prev
    Next
    INDEX
    Explanations

    to infinitive verbs

    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
    ä¸Ģéĺµ
    -0.11
    ä¸ĢæŶ
    -0.10
    çªĿ
    -0.09
    æľīä¸Ģç§į
    -0.09
    æľīå¤ļ
    -0.09
    æıŃ
    -0.08
    忽
    -0.08
    -publish
    -0.08
    TimeString
    -0.08
    åı¦æľī
    -0.08
    POSITIVE LOGITS
    åıijè¨Ģ
    0.11
    åıijæĮ¥ä½ľçĶ¨
    0.09
    åĩ«
    0.09
     asses
    0.08
    aires
    0.08
    æĬĬè¿ĻäºĽ
    0.08
    èĿī
    0.08
    åĸĺ
    0.08
    èĤł
    0.08
    éĹ»
    0.08
    Activations Density 0.022%

    No Known Activations