© 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. 55622
    Prev
    Next
    INDEX
    Explanations

    automation and automated processes

    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
    ses
    -0.12
     Excell
    -0.10
    quis
    -0.09
    ities
    -0.09
    her
    -0.09
    оÑģ
    -0.09
    /from
    -0.08
    ÑĢабаÑĤ
    -0.08
    ivant
    -0.08
    ×ķת
    -0.08
    POSITIVE LOGITS
    èįļ
    0.11
    çĦ¶æĺ¯
    0.10
    ány
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    лиÑģÑĤ
    0.09
     обÑıзан
    0.09
    äºĨä¸įå°ij
    0.09
    äºĨ许å¤ļ
    0.09
    宵
    0.08
    çĺ¿
    0.08
    Activations Density 0.016%

    No Known Activations