© 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. 61365
    Prev
    Next
    INDEX
    Explanations

    preposition followed by a noun

    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
     Buckley
    -0.10
    ä¸ĩ人
    -0.09
    èĽĽ
    -0.09
    ISO
    -0.08
    æŃ¢
    -0.08
    بÙĦاد
    -0.08
    ié
    -0.08
     caf
    -0.08
    IES
    -0.08
    CAF
    -0.08
    POSITIVE LOGITS
     both
    0.10
    æĢģ
    0.10
    ä¸įçĶĺ
    0.10
    çĶ¨æĪ·æıIJä¾Ľ
    0.10
    广大
    0.09
    轩
    0.09
    èĥĥåı£
    0.09
    è°Ľ
    0.09
    èģĮ
    0.09
    éĥĵ
    0.09
    Activations Density 0.012%

    No Known Activations