© 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. 56842
    Prev
    Next
    INDEX
    Explanations

    words after common function words

    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
    çĻ£
    -0.11
    åıĺæĢģ
    -0.10
    ä¸ĩäºĭ
    -0.10
    çħ§
    -0.09
    涯
    -0.09
    çİĻ
    -0.09
    _dispatcher
    -0.09
    ãĥ¼ãĥł
    -0.09
    .vaadin
    -0.09
    æī¾äºĨ
    -0.09
    POSITIVE LOGITS
    è§Ĥçľĭ
    0.16
    è§Ĥä¼Ĺ
    0.14
    è§Ĥèµı
    0.13
    çľĭå®Į
    0.12
    æĦŁåĬ¨
    0.12
     viewers
    0.12
    è´Ńä¹°
    0.12
    åıĹä¼Ĺ
    0.12
    åIJ¬ä¼Ĺ
    0.11
    éĺħ读
    0.11
    Activations Density 0.282%

    No Known Activations