© 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. 39503
    Prev
    Next
    INDEX
    Explanations

    Maine

    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
    uels
    -0.10
    ãģ¹ãģį
    -0.09
    InBackground
    -0.09
    aben
    -0.09
    å°Ķæĸ¯
    -0.09
    nels
    -0.09
    hips
    -0.09
    imes
    -0.08
    ulo
    -0.08
    åįĹæ²Ļ
    -0.08
    POSITIVE LOGITS
    าะ
    0.10
     Maine
    0.10
    orable
    0.09
    -born
    0.09
    ĭ
    0.09
    ois
    0.09
    stry
    0.09
    Ỽ
    0.09
    ÑģÑĤÑĢ
    0.09
    è¯Ŀ
    0.09
    Activations Density 0.005%

    No Known Activations