© 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. 19704
    Prev
    Next
    INDEX
    Explanations

    as expected or as always

    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
    -Mart
    -0.09
    以èĩ³äºİ
    -0.08
    Powered
    -0.08
    _NS
    -0.08
    彤
    -0.08
    atego
    -0.08
    åĪĽä½ľèĢħ
    -0.08
    бÑĢо
    -0.08
     Implemented
    -0.08
    èĪ¶
    -0.08
    POSITIVE LOGITS
     usual
    0.30
    usual
    0.23
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    0.21
    以å¾Ģ
    0.20
    æĥ¯ä¾ĭ
    0.15
    ä¸Ģå¦Ĥ
    0.15
     customary
    0.15
    常è§Ħ
    0.14
    ä¾Ŀæŧæĺ¯
    0.14
    å¾Ģ
    0.14
    Activations Density 0.081%

    No Known Activations