© 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. 4580
    Prev
    Next
    INDEX
    Explanations

    agreement or transition

    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
    ä¸Ģä½ĵ
    -0.10
    kick
    -0.09
    erie
    -0.09
     Pane
    -0.09
    gef
    -0.08
    äºĴåĬ©
    -0.08
    Kick
    -0.08
    mith
    -0.08
    E
    -0.08
    maker
    -0.08
    POSITIVE LOGITS
    lahoma
    0.10
    -sized
    0.10
    说æĺ¯
    0.10
    åľ¨æĪijçļĦ
    0.09
    ridge
    0.09
    ibri
    0.09
     sized
    0.09
    就说
    0.09
    tober
    0.09
    fried
    0.09
    Activations Density 0.012%

    No Known Activations