© 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. 31174
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating position or relation

    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
    缣
    -0.10
    ensis
    -0.10
    æĹłç¼ĺ
    -0.09
    æĵİ
    -0.09
    æĭ¿èµ·
    -0.09
    ennis
    -0.09
    åīĬ
    -0.08
     Cry
    -0.08
     helicopt
    -0.08
    åķĦ
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.12
    aber
    0.09
    çļĦæĺ¯
    0.09
    éķ¿éĢĶ
    0.08
    æīĵå¾Ĺ
    0.08
    大å±Ģ
    0.08
    ãģĿãĤĮãģ«
    0.08
    ToPoint
    0.08
    èĭĭ
    0.08
    td
    0.08
    Activations Density 0.067%

    No Known Activations