© 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. 47814
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
    æľªç»ıæİĪæĿĥ
    -0.09
    Tap
    -0.08
    uits
    -0.08
    otten
    -0.08
    imb
    -0.08
    ople
    -0.08
    ãĥ¼ãĥĹ
    -0.08
     tap
    -0.08
    tap
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    POSITIVE LOGITS
    缴è¾ĸ
    0.10
    ä½Ĩå¦Ĥæŀľ
    0.10
    æ·
    0.09
    alm
    0.09
    ä¸ĩéĩĮ
    0.09
    使çĶ¨å¯¿åij½
    0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.09
    ä¸ī天
    0.09
     regress
    0.09
    åĪ°åľº
    0.09
    Activations Density 0.054%

    No Known Activations