© 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. 31576
    Prev
    Next
    INDEX
    Explanations

    and followed by possessives or descriptions

    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
    unfold
    -0.09
    .sul
    -0.09
    以ä¸ĭæĺ¯
    -0.09
    ANTS
    -0.09
    imers
    -0.09
     Collins
    -0.09
    ç²ij
    -0.09
    .ol
    -0.09
    ewe
    -0.09
    为æ°ij
    -0.09
    POSITIVE LOGITS
    ä»ĸãģ®
    0.09
     other
    0.09
    è¢«åĽ°
    0.09
    æĺĶæĹ¥
    0.09
    è°ģéĥ½
    0.09
    éĢĿ
    0.09
     counterpart
    0.08
    ä¸įä½ı
    0.08
     others
    0.08
    缸åħ³äººåijĺ
    0.08
    Activations Density 0.219%

    No Known Activations