© 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. 63115
    Prev
    Next
    INDEX
    Explanations

    now, currently, today, instead

    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
    åĨį次
    -0.09
    æ´»
    -0.09
     hete
    -0.08
    çĹŀ
    -0.08
    ä¸į容
    -0.08
    itemName
    -0.08
    Jur
    -0.08
     Ñģнова
    -0.08
    imity
    -0.08
    AFF
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.31
    çİ°æľī
    0.27
     currently
    0.25
     existing
    0.25
    缮åīį
    0.25
    Currently
    0.24
    çİ°çĬ¶
    0.24
    å·²æľī
    0.23
    çİ°è¡Į
    0.22
    currently
    0.22
    Activations Density 0.526%

    No Known Activations