© 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. 56295
    Prev
    Next
    INDEX
    Explanations

    giant, monstrous, titan, behemoth, beast

    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
    aris
    -0.08
    лад
    -0.08
    ç¿ł
    -0.08
    .getHost
    -0.08
    åĬ©çIJĨ
    -0.08
    ãģIJ
    -0.08
     Tra
    -0.08
     Ecc
    -0.08
     Verd
    -0.07
    产åĵģçļĦ
    -0.07
    POSITIVE LOGITS
    巨人
    0.13
    åºŀ大çļĦ
    0.11
    å±¹
    0.11
    身躯
    0.10
    å·¨
    0.10
    æĭĨ
    0.10
    åŁİ乡å±ħæ°ij
    0.10
    åł¡åŀĴ
    0.10
    åºŀ大
    0.10
    强大çļĦ
    0.10
    Activations Density 0.026%

    No Known Activations