© 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. 19715
    Prev
    Next
    INDEX
    Explanations

    asking or meaning

    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
    ç¢į
    -0.10
     Kurd
    -0.09
    akra
    -0.09
    åĬ³
    -0.09
    .stub
    -0.08
    .va
    -0.08
    æĬµ
    -0.08
     Sandwich
    -0.08
    iglia
    -0.08
    çªĴ
    -0.08
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.10
    æŁIJç§į
    0.10
    èĢĮæĺ¯
    0.09
    çĻ»ä¸Ĭ
    0.09
    quire
    0.09
    æ³ī
    0.09
    ä¸ĬäºĨ
    0.09
     something
    0.09
    åħĪ导
    0.08
    æŁIJ个
    0.08
    Activations Density 0.225%

    No Known Activations