© 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. 61800
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions leading to nouns

    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
    URT
    -0.11
    大å¥ĸ
    -0.09
    å´ĸ
    -0.09
    èĽĢ
    -0.09
    å¾ĹçĽĬ
    -0.09
    onda
    -0.09
    cura
    -0.08
     trap
    -0.08
    icit
    -0.08
    iej
    -0.08
    POSITIVE LOGITS
     for
    0.11
    以åħ¶
    0.10
     wegen
    0.10
    æıIJéĢŁ
    0.09
    åĽłä¸ºä»ĸ
    0.09
     за
    0.09
    สำ
    0.09
    åĽłåħ¶
    0.09
    ForKey
    0.08
    å¾Īæ·±
    0.08
    Activations Density 0.125%

    No Known Activations