© 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. 50295
    Prev
    Next
    INDEX
    Explanations

    will + verb

    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
    åĽ½æĥħ
    -0.09
    æģĥ
    -0.09
    allah
    -0.09
    æĪİ
    -0.09
    plist
    -0.09
    ecess
    -0.09
    被æī§è¡Į
    -0.09
    çIJĨ解åĴĮ
    -0.09
    ä¸Ģå¤ľ
    -0.08
    åĪĿ次
    -0.08
    POSITIVE LOGITS
    åĨ²
    0.08
    æīĭèĩĤ
    0.08
    iske
    0.08
    istro
    0.08
    é¼ĵ
    0.08
    æĬĬ
    0.08
    åĬªåĬĽ
    0.08
    ä¼´
    0.08
    isk
    0.08
    æī¬
    0.08
    Activations Density 0.036%

    No Known Activations