© 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. 22081
    Prev
    Next
    INDEX
    Explanations

    put followed by preposition

    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
    æļĿ
    -0.11
    å¾Ĺ天
    -0.10
    roys
    -0.10
    hdl
    -0.10
    èĩªå·±
    -0.10
    æĿª
    -0.10
    iten
    -0.09
    å¸ı
    -0.09
    åľ¨è¿ĩ渡
    -0.09
    帷
    -0.09
    POSITIVE LOGITS
    éħª
    0.10
    mand
    0.09
    able
    0.08
    åĩºæĿ¥
    0.08
    大èĩªçĦ¶
    0.08
    éļı
    0.08
     ÑģпÑĢав
    0.08
    aways
    0.08
    åѤçĭ¬
    0.08
    é³Ħ
    0.08
    Activations Density 0.014%

    No Known Activations