© 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. 49575
    Prev
    Next
    INDEX
    Explanations

    admission and entrance fees

    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
    ä¹Ŀå¹´
    -0.10
    burst
    -0.09
    ç»Ħç»ĩå®ŀæĸ½
    -0.09
    ä¼ļéķ¿
    -0.09
    èªĬ
    -0.09
    è´Łè´£ä»»
    -0.09
    èļ´
    -0.09
     оÑĤдÑĭÑħ
    -0.08
     пÑĢедоÑģÑĤ
    -0.08
     lá»Ļ
    -0.08
    POSITIVE LOGITS
    vig
    0.09
     Kash
    0.08
    åĴĮæĶ¯æĮģ
    0.08
    èŁ²
    0.08
    alon
    0.08
    codec
    0.08
    ä¸Ģå¹ħ
    0.08
    icha
    0.08
    .Net
    0.08
    inst
    0.08
    Activations Density 0.005%

    No Known Activations