© 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. 34963
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun/adjective

    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
    å¾Īå¤ļäºĭæĥħ
    -0.12
    ä»Ģä¹Īéĥ½ä¸į
    -0.11
    对å¾ħ
    -0.11
     оÑĦоÑĢм
    -0.10
     мом
    -0.10
    å¾ħéģĩ
    -0.09
    èģĶç³»æĪij们
    -0.09
    使çĶ¨æĿĥ
    -0.09
    åıijæĮ¥
    -0.09
    çļĦ姿æĢģ
    -0.09
    POSITIVE LOGITS
    åĶī
    0.10
    ipi
    0.09
    -FIRST
    0.08
    PRESS
    0.08
    讨
    0.08
    æ°¸è¿ľ
    0.08
     Brooks
    0.08
    åĥŃ
    0.08
    çİ®
    0.08
    toMatchSnapshot
    0.08
    Activations Density 0.006%

    No Known Activations