© 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. 35522
    Prev
    Next
    INDEX
    Explanations

    with / avec / dengan

    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
    顺
    -0.10
    Ợ
    -0.09
    ä¼Ĺ人
    -0.09
    AGIC
    -0.09
    åľ°ä¸Ń
    -0.09
    æį£
    -0.09
    æĿ¥çľĭçľĭåIJ§
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    åĶĽ
    -0.09
    /lic
    -0.08
    POSITIVE LOGITS
     with
    0.24
     vỼi
    0.22
    with
    0.21
     dengan
    0.19
     avec
    0.19
    _with
    0.17
    	with
    0.17
    avec
    0.16
    ewith
    0.15
    With
    0.15
    Activations Density 0.523%

    No Known Activations