© 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. 35028
    Prev
    Next
    INDEX
    Explanations

    very + adjective

    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
    opus
    -0.10
    æĽ´å¤ļä¿¡æģ¯
    -0.10
    èĭ¥å¹²
    -0.10
     ÑģооÑĤвеÑĤ
    -0.09
    ä¸ŃéĹ´
    -0.09
    è´¸
    -0.09
     htonl
    -0.09
     поÑĩем
    -0.09
    eln
    -0.08
    isan
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.10
    åī
    0.09
    大çļĦ
    0.09
    妤
    0.09
    oting
    0.09
    oted
    0.09
    级åĪ«çļĦ
    0.09
    ç¼Ĩ
    0.09
    好è¯Ħ
    0.08
    çŁ¥åIJįçļĦ
    0.08
    Activations Density 0.049%

    No Known Activations