© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36461
    Prev
    Next
    INDEX
    Explanations

    meanwhile

    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
    æľ«
    -0.09
    秫
    -0.09
    åİĨ代
    -0.09
    å®Ļ
    -0.09
     eventually
    -0.09
    ä¼Ĺ人
    -0.08
    è¿ĽèĢĮ
    -0.08
    åĮħ袱
    -0.08
    одеÑĢж
    -0.08
    .prot
    -0.08
    POSITIVE LOGITS
    åı¦ä¸Ģ
    0.17
    åı¦ä¸Ģè¾¹
    0.16
    Meanwhile
    0.15
     Meanwhile
    0.15
    åı¦ä¸Ģæĸ¹éĿ¢
    0.14
     meanwhile
    0.14
    åı¦å¤ĸä¸Ģ个
    0.13
    åı¦ä¸Ģç§į
    0.13
    ä¸İæѤåIJĮæŶ
    0.12
     elsewhere
    0.12
    Activations Density 0.054%

    No Known Activations