© 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. 7381
    Prev
    Next
    INDEX
    Explanations

    falling into categories or groups

    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
    (pdf
    -0.10
    ByKey
    -0.09
    æłĩçļĦ
    -0.09
    èĴĤ
    -0.09
    presence
    -0.09
    èĥ§
    -0.09
    marshall
    -0.09
    è¯Ħè®®
    -0.09
    åĬ²
    -0.08
    èĢ¸
    -0.08
    POSITIVE LOGITS
     category
    0.19
    èĮĥçķ´
    0.18
    ä¸Ģç±»
    0.17
    两类
    0.16
     categories
    0.15
    ç±»åĪ«
    0.15
     каÑĤегоÑĢии
    0.15
    category
    0.14
    å±ŀäºİ
    0.14
    æѤ类
    0.14
    Activations Density 0.088%

    No Known Activations