© 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. 5382
    Prev
    Next
    INDEX
    Explanations

    information or details

    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
    ivable
    -0.09
    rax
    -0.09
    å¹³æŶ
    -0.09
    NIC
    -0.09
    åį¿
    -0.09
    å¼ĢåıijåĪ©çĶ¨
    -0.08
    èIJ¥ä¸ļé¢Ŀ
    -0.08
    åIJĬ
    -0.08
    ä¸Ģåı¥
    -0.08
    builtin
    -0.08
    POSITIVE LOGITS
    详æĥħ
    0.13
    ç»ĨåĪĻ
    0.12
    ç»ĨèĬĤ
    0.12
    详ç»Ĩä»ĭç»į
    0.11
    详ç»ĨçļĦ
    0.11
    _details
    0.10
    åħ¨é¢Ŀ
    0.10
    详ç»Ĩ
    0.10
    æĴŃ
    0.09
    管çIJĨåĬŀæ³ķ
    0.09
    Activations Density 0.029%

    No Known Activations