© 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. 10795
    Prev
    Next
    INDEX
    Explanations

    young + noun

    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
    rud
    -0.11
    ting
    -0.11
    骧
    -0.10
    ä¸įæ¸ħ
    -0.10
    hog
    -0.10
    ä½Ĺ
    -0.10
    ãģ£ãģįãĤĬ
    -0.09
    ween
    -0.09
    oled
    -0.09
    踵
    -0.09
    POSITIVE LOGITS
    blood
    0.14
    ish
    0.12
    (er
    0.12
    lings
    0.11
    ling
    0.11
    stown
    0.11
    ify
    0.10
    est
    0.10
    sville
    0.10
    ESIS
    0.10
    Activations Density 0.027%

    No Known Activations