© 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. 30169
    Prev
    Next
    INDEX
    Explanations

    audio mixing and remixing

    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
    orary
    -0.11
    lags
    -0.10
    ement
    -0.10
    ment
    -0.10
    åģļèµ·
    -0.09
    elda
    -0.09
     воз
    -0.09
    èµĦ产管çIJĨ
    -0.08
    æľī趣çļĦ
    -0.08
    产åĩº
    -0.08
    POSITIVE LOGITS
    tape
    0.10
    tur
    0.10
    æĴº
    0.09
    æĿĤ
    0.09
    ué
    0.08
    樽
    0.08
    æ±²
    0.08
    æĪİ
    0.08
    _dispatch
    0.08
    upe
    0.08
    Activations Density 0.008%

    No Known Activations