© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37883
    Prev
    Next
    INDEX
    Explanations

    verbs of action or 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°º
    -0.11
    -0.10
    ä¸Ģ大åłĨ
    -0.10
    ç¾ģ
    -0.09
    æĺ¯ä¸Ģ件
    -0.09
    è°ģéĥ½
    -0.09
    æŶéĹ´ä¸º
    -0.09
    鸳
    -0.09
    许åı¯
    -0.09
    artz
    -0.09
    POSITIVE LOGITS
     лиÑĪÑĮ
    0.10
    igr
    0.09
    ÑģÑı
    0.09
    -fw
    0.09
    Č
    0.09
     sobie
    0.09
     دائÙħا
    0.08
    ÑĦÑĢ
    0.08
     samen
    0.08
    FFE
    0.08
    Activations Density 0.205%

    No Known Activations