© 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. 57456
    Prev
    Next
    INDEX
    Explanations

    linking verb followed by state

    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
    å·²ç»ıæľī
    -0.10
     оÑĤкÑĢÑĭва
    -0.10
    ssf
    -0.10
    å·²ç»ıæľīäºĨ
    -0.10
    IBE
    -0.09
    íķĦ
    -0.09
    éľĨ
    -0.09
    æĭĽå¾ħ
    -0.09
    vero
    -0.09
     пока
    -0.08
    POSITIVE LOGITS
    4
    0.10
    3
    0.10
    å®Įå·¥
    0.09
    2
    0.09
    8
    0.09
    åħ¨é¢Ŀ
    0.09
    å½»åºķ
    0.09
     fully
    0.08
    5
    0.08
    æģ°å½ĵ
    0.08
    Activations Density 0.045%

    No Known Activations