© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    material types and properties

    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
    æīįæĺ¯çľŁæŃ£
    -0.09
    åı£æ°´
    -0.09
    aż
    -0.08
    两款
    -0.08
    西
    -0.08
    éĺī
    -0.08
    åĪº
    -0.08
    ä¸Ģ款
    -0.08
    è¯ģå®ŀ
    -0.08
    çĶij
    -0.08
    POSITIVE LOGITS
    ç»Ļ人
    0.10
    setLayout
    0.10
    æ¸Ĭ
    0.09
    ä½ľèĢħæľ¬äºº
    0.09
    强度
    0.09
    天çĦ¶
    0.09
    æŁĶ
    0.09
    iron
    0.09
    éĩįçĶŁ
    0.09
    éĩįå·¥
    0.09
    Activations Density 0.076%

    No Known Activations