© 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. 34718
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    beck
    -0.09
    atel
    -0.09
    بÙĬÙĦ
    -0.09
    æľĪåºķ
    -0.09
    æľĪåĪĿ
    -0.08
    bol
    -0.08
     Shed
    -0.08
    iph
    -0.08
    بدا
    -0.08
     beginning
    -0.08
    POSITIVE LOGITS
    ells
    0.10
    娣
    0.09
    æ»ĺ
    0.09
    好åIJĹ
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    åIJ¬å¾Ĺ
    0.09
    åģļçļĦäºĭ
    0.09
    getIndex
    0.08
    å®ĺ宣
    0.08
    doi
    0.08
    Activations Density 0.016%

    No Known Activations