© 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. 10614
    Prev
    Next
    INDEX
    Explanations

    roman numerals or lists

    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
    éĺµéĺµ
    -0.11
    wart
    -0.10
    .kotlin
    -0.10
    extView
    -0.09
    æ²±
    -0.09
    áĥĹ
    -0.09
    æ¶Ķ
    -0.09
    erland
    -0.09
    HORT
    -0.09
    åħĥæŦ
    -0.09
    POSITIVE LOGITS
    archy
    0.10
    æĪĺèĥľ
    0.09
    ãģļ
    0.09
    æĢ§åĴĮ
    0.09
    ìĶ©
    0.08
    ãģĤãģŁãĤĬ
    0.08
    ãĢħ
    0.08
    åħļåĴĮ
    0.08
    个å¤ļ
    0.08
    人大
    0.08
    Activations Density 0.334%

    No Known Activations