© 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. 27490
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    åıĮåıĮ
    -0.10
     Champ
    -0.10
    rete
    -0.09
    è¿ijä¹İ
    -0.09
    æ¯ı个人éĥ½
    -0.09
    é«ĺè¾¾
    -0.09
    æ»ij
    -0.08
    izon
    -0.08
    beat
    -0.08
    糸
    -0.08
    POSITIVE LOGITS
    对该
    0.18
    è¯¥æł¡
    0.15
    è¯¥é¡¹çĽ®
    0.13
    该æĿij
    0.13
     íķ´ëĭ¹
    0.13
    該
    0.12
    该
    0.12
    å½ĵåľ°çļĦ
    0.12
     nearby
    0.12
    åIJĮç±»
    0.12
    Activations Density 0.306%

    No Known Activations