© 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. 62585
    Prev
    Next
    INDEX
    Explanations

    great adjectives

    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
    éĵĥ
    -0.10
    inton
    -0.09
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    çİĩè¾¾åĪ°
    -0.09
    ptions
    -0.09
    æŃ»è§Ĵ
    -0.09
    被æįķ
    -0.09
    éķ¿åŁİ
    -0.08
    çŃ¹
    -0.08
    aggi
    -0.08
    POSITIVE LOGITS
    -grand
    0.11
    åŃĹåı·
    0.10
    -volume
    0.10
    æĹ¥åŃIJ
    0.09
    /small
    0.09
    enance
    0.09
    /Area
    0.09
    /big
    0.09
    é©ļ
    0.09
    æģ¸
    0.09
    Activations Density 0.031%

    No Known Activations