© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20841
    Prev
    Next
    INDEX
    Explanations

    "for example" or "e.g."

    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
    æŃ¤äºº
    -0.09
    åĤ¨èĥ½
    -0.09
    çĴľ
    -0.09
    åı¦ä¸Ģç§į
    -0.09
    çĽ¸å¯¹æĿ¥è¯´
    -0.09
    .IGNORE
    -0.08
    æľĢåħ³éĶ®
    -0.08
    åIJĦæł·
    -0.08
    åıįæŃ£
    -0.08
    æľīç§į
    -0.08
    POSITIVE LOGITS
    æ¯Ķå¦Ĥ
    0.27
    ä¾ĭå¦Ĥ
    0.25
    ä¾ĭãģĪãģ°
    0.23
    æ¯Ķå¦Ĥ说
    0.23
     ÐĿапÑĢимеÑĢ
    0.20
    èѬå¦Ĥ
    0.18
    напÑĢимеÑĢ
    0.17
     eg
    0.13
     ׾×ŀש׾
    0.13
    апÑĢимеÑĢ
    0.13
    Activations Density 0.265%

    No Known Activations