© 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. 34372
    Prev
    Next
    INDEX
    Explanations

    intensifiers of magnitude or degree

    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
    æľīå¤ļä¹Ī
    -0.09
    åĵī
    -0.09
    æŀģ为
    -0.09
    æľĢåħĪè¿ĽçļĦ
    -0.08
    æŀģåħ¶
    -0.08
    çĭ¬æľīçļĦ
    -0.08
    ãģĻãģİãģ¦
    -0.08
     здоÑĢов
    -0.08
    Former
    -0.08
    Selectable
    -0.08
    POSITIVE LOGITS
     somewhat
    0.10
    å°ijãģĹ
    0.10
     slightly
    0.09
    KE
    0.09
    ç¨įå¾®
    0.09
    æ©Ħæ¦Ħ
    0.09
    ä¹Łæ¯Ķè¾ĥ
    0.09
    oton
    0.09
    éĵĬ
    0.09
    utton
    0.09
    Activations Density 0.572%

    No Known Activations