© 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. 57975
    Prev
    Next
    INDEX
    Explanations

    would like 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
    ä¸įæĩĪ
    -0.10
    åŃº
    -0.10
    çĴ§
    -0.09
    å£ķ
    -0.09
    ç²²
    -0.09
    è¾Ĥ
    -0.09
    ucus
    -0.09
    meld
    -0.08
    åĪ©åĻ¨
    -0.08
    iot
    -0.08
    POSITIVE LOGITS
    berman
    0.10
    à¸Ńา
    0.09
    äºĨä¸Ģ份
    0.09
    è¿ĻèĪ¬
    0.08
    主æĦı
    0.08
    æĬķ身
    0.08
    第ä¸īèĢħ
    0.08
     vòng
    0.08
     forfe
    0.08
    /pass
    0.08
    Activations Density 0.032%

    No Known Activations