© 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. 53472
    Prev
    Next
    INDEX
    Explanations

    as they

    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
    ìĬµ
    -0.09
    åĢ¡
    -0.09
    åĪ°åºķ
    -0.09
    ä¿Ĥ
    -0.08
     Gow
    -0.08
    æĹłç¼ĺ
    -0.08
    è¶ħ级
    -0.08
    åĮĪ
    -0.08
    adiator
    -0.08
    .wx
    -0.08
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.11
    ç½Ķ
    0.09
    ä¸ĭéĿ¢
    0.09
    çĩİ
    0.09
    å¦Ĥä¸ĭ
    0.09
    åĽ¾
    0.09
    å¦Ļ
    0.09
     proved
    0.08
    转移åĪ°
    0.08
     Rap
    0.08
    Activations Density 0.045%

    No Known Activations