© 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. 31404
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by word

    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
    è¿ĻäºĽéĹ®é¢ĺ
    -0.09
    竺
    -0.09
    bear
    -0.08
    å´¤
    -0.08
     Cros
    -0.08
    ä»ħ代表
    -0.08
    -*-
    -0.08
    ona
    -0.08
    è¿ŀäºij
    -0.08
    abouts
    -0.08
    POSITIVE LOGITS
    ãĢģ“
    0.10
    /OR
    0.09
    éĵĦ
    0.09
    ishop
    0.09
    KER
    0.09
    aro
    0.09
    atie
    0.08
    åīį线
    0.08
    æµ¥
    0.08
    aginator
    0.08
    Activations Density 0.384%

    No Known Activations