© 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. 22457
    Prev
    Next
    INDEX
    Explanations

    eosin, EF, verbose

    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
    ature
    -0.09
    kind
    -0.08
    4
    -0.08
    西äºļ
    -0.08
    chen
    -0.08
    ialog
    -0.08
    ãĤµãĥ©
    -0.08
    0
    -0.08
    5
    -0.07
    â
    -0.07
    POSITIVE LOGITS
    æĹłå£°
    0.10
    责任åĪ¶
    0.10
    CharCode
    0.10
    shan
    0.09
     вÑĭÑĢажен
    0.09
    VERBOSE
    0.09
    smith
    0.09
    .ribbon
    0.09
     dÄ±ÅŁÄ±
    0.09
    æ¾Ħ
    0.09
    Activations Density 0.008%

    No Known Activations