© 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. 18037
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming, or mathematical expressions

    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
    ãģ¨ãģ«ãģĭ
    -0.11
    âģĩ
    -0.11
     اÙĦÙĦج
    -0.10
    ⤴
    -0.10
    ãĤ¿ãĤ¤ãĥŁ
    -0.10
    ãģ¨ãĤĬãģĤ
    -0.10
     اÙĦجÙĩا
    -0.10
    ãįī
    -0.10
     اÙĦÙħرأ
    -0.09
    ãģĬäºĴ
    -0.09
    POSITIVE LOGITS
    <|endoftext|>
    0.08
    /trans
    0.06
    /
    0.06
     E
    0.06
     S
    0.06
    /post
    0.06
    ferred
    0.06
     A
    0.05
    atable
    0.05
     x
    0.05
    Activations Density 9.120%

    No Known Activations