© 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. 31817
    Prev
    Next
    INDEX
    Explanations

    practice and its applications

    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
    ness
    -0.12
     tract
    -0.09
    lify
    -0.09
    çĦ¶æĺ¯
    -0.08
    play
    -0.08
    人å¿ĥ
    -0.08
    çĴŀ
    -0.08
    worth
    -0.08
    red
    -0.08
    zte
    -0.08
    POSITIVE LOGITS
    itioner
    0.13
    ively
    0.11
    ABLE
    0.11
    able
    0.11
    icable
    0.10
    ·æĸ°
    0.09
    ables
    0.09
    uelles
    0.09
    itia
    0.09
     اÙĦدÙĨÙĬا
    0.08
    Activations Density 0.037%

    No Known Activations