© 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. 57171
    Prev
    Next
    INDEX
    Explanations

    love and related concepts

    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
    ond
    -0.11
    imal
    -0.09
    åģļåĪ°
    -0.09
    UnderTest
    -0.09
    AW
    -0.09
    Eta
    -0.09
    æĥ³æĥ³
    -0.08
     nhiên
    -0.08
    iment
    -0.08
    or
    -0.08
    POSITIVE LOGITS
    ษา
    0.13
    fully
    0.12
    liest
    0.10
    -hearted
    0.10
    ably
    0.09
    обилÑĮ
    0.09
    æħķ
    0.09
    ofs
    0.09
    RET
    0.09
    æĥľ
    0.09
    Activations Density 0.064%

    No Known Activations