© 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. 31240
    Prev
    Next
    INDEX
    Explanations

    hypothetical consequence

    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
    æ·³
    -0.10
    ked
    -0.08
    ä¸ĩä¸Ģ
    -0.08
    æŦ
    -0.08
    atch
    -0.08
     derby
    -0.08
    4
    -0.08
    reeze
    -0.08
    1
    -0.07
    ä¿Ŀå®Ī
    -0.07
    POSITIVE LOGITS
    æµ·å²Ľ
    0.11
    æľīå¾Īå¤ļç§į
    0.11
    å«Į
    0.10
    æī¿åĬŀ
    0.10
    irim
    0.10
    nev
    0.10
    ç«ĭåĪ»
    0.10
    ลà¸ļ
    0.10
    çł´éŨ
    0.10
     налогов
    0.10
    Activations Density 0.032%

    No Known Activations