© 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. 49884
    Prev
    Next
    INDEX
    Explanations

    MATLAB and Scilab code functions

    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
    éĦĦ
    -0.09
    åĿ¨
    -0.09
    æ»ı
    -0.08
    cls
    -0.08
    çݯç»ķ
    -0.08
    Chief
    -0.08
    pray
    -0.08
    ingly
    -0.08
    urr
    -0.08
     Reco
    -0.08
    POSITIVE LOGITS
     varargin
    0.13
     MATLAB
    0.13
     nargin
    0.12
    (varargin
    0.10
    (fullfile
    0.10
    å¼Ħ
    0.10
    éĻ¢
    0.10
     numel
    0.10
    æµĻæ±Łå¤§åѦ
    0.10
    æµĻ
    0.09
    Activations Density 0.135%

    No Known Activations