© 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. 35126
    Prev
    Next
    INDEX
    Explanations

    thin layer

    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
     Ple
    -0.08
    ãģĵãģ¨ãģ«
    -0.08
    казалоÑģÑĮ
    -0.07
    ä¸Ģ棵
    -0.07
    Bulk
    -0.07
     Immutable
    -0.07
     cabbage
    -0.07
    æ²®
    -0.07
     unc
    -0.07
    èī¯
    -0.07
    POSITIVE LOGITS
    åİļåİļçļĦ
    0.16
    å±Ĥ
    0.15
     layer
    0.15
    ä¸Ģå±Ĥ
    0.15
    layer
    0.14
    層
    0.13
     layers
    0.12
    èĸĦ
    0.12
    (layer
    0.12
    -layer
    0.12
    Activations Density 0.069%

    No Known Activations