© 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. 50846
    Prev
    Next
    INDEX
    Explanations

    ethical standards

    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
    zelf
    -0.10
    деÑģÑıÑĤ
    -0.10
    itting
    -0.10
    ession
    -0.09
    uar
    -0.09
    naire
    -0.09
    éĽ³
    -0.09
    anten
    -0.08
    ä¿Ŀå§Ĩ
    -0.08
    ä¸įå¿ħè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
    ised
    0.15
    mÃ¤ÃŁig
    0.13
    bred
    0.12
    ize
    0.12
    IZED
    0.11
    -issue
    0.11
    æĦıä¹īä¸ĬçļĦ
    0.10
    ized
    0.10
    izing
    0.10
    izedName
    0.10
    Activations Density 0.056%

    No Known Activations