© 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. 4667
    Prev
    Next
    INDEX
    Explanations

    sq. ft. / shares / votes / acres / fewer / Views

    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
    erator
    -0.09
    ä¸Ģå°ı
    -0.08
     Cassidy
    -0.08
    车èģĶç½ij
    -0.08
    ä¸Ģä¼ļ
    -0.08
    manship
    -0.08
    åĨįå¤ļ
    -0.08
    èĥŃ
    -0.08
    еÑĩа
    -0.08
    nob
    -0.08
    POSITIVE LOGITS
    /-
    0.10
    ickers
    0.08
    ãģ©ãģĵãĤį
    0.08
    orsi
    0.08
     bite
    0.08
    ä¸ŃéĢĶ
    0.08
    夫å¦ĩ
    0.08
     пÑĥнкÑĤ
    0.08
    anding
    0.07
    ennon
    0.07
    Activations Density 0.090%

    No Known Activations