© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20294
    Prev
    Next
    INDEX
    Explanations

    code delimiters and quotations

    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
    artment
    -0.08
    amente
    -0.08
     dÃły
    -0.08
     Pablo
    -0.08
    .getSelection
    -0.08
    ä»Ģ
    -0.08
    EMBER
    -0.08
     bữa
    -0.08
    çªľ
    -0.08
    以èī²åĪĹ
    -0.08
    POSITIVE LOGITS
    ../../../
    0.10
    å¿
    0.09
    ened
    0.09
    è¾ķ
    0.09
    åľ¨å®¶
    0.08
    åľ¨ä¸Ģ
    0.08
    ated
    0.08
    æĺ¯å¾Ī
    0.08
    æ§Ľ
    0.08
    罨
    0.08
    Activations Density 0.110%

    No Known Activations