© 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. 5887
    Prev
    Next
    INDEX
    Explanations

    Glen names

    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
    æĢ§å¼º
    -0.10
    ames
    -0.09
    iddle
    -0.09
    ×Ļר
    -0.09
    ity
    -0.08
    arro
    -0.08
    isible
    -0.08
    ly
    -0.08
    éłħ
    -0.08
    ãģıãĤĮ
    -0.08
    POSITIVE LOGITS
    ters
    0.13
    èĩ¾
    0.13
    halb
    0.11
    ocol
    0.09
    ties
    0.09
    going
    0.09
    ç»ļ
    0.09
    ention
    0.09
    çŃ·
    0.09
    chas
    0.09
    Activations Density 0.013%

    No Known Activations