© 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. 19141
    Prev
    Next
    INDEX
    Explanations

    custom made items

    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
    åĤį
    -0.09
    yll
    -0.09
    caler
    -0.08
    åĨľåī¯
    -0.08
    æ¸ħæĸ°
    -0.08
    çľ¼ä¸ĭ
    -0.08
    emas
    -0.08
    /crypto
    -0.08
    ackers
    -0.08
     expectedResult
    -0.08
    POSITIVE LOGITS
    å®ļåĪ¶
    0.28
     custom
    0.19
     customization
    0.18
    custom
    0.18
    -custom
    0.17
    (custom
    0.17
     customize
    0.17
    个æĢ§åĮĸ
    0.17
    /custom
    0.17
     Custom
    0.16
    Activations Density 0.077%

    No Known Activations