© 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. 55855
    Prev
    Next
    INDEX
    Explanations

    happy thing, medium, patients, kid, Thanksgiving, memories, couple

    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
    ORD
    -0.09
    å¯ĩ
    -0.09
    arity
    -0.09
    âį¨
    -0.08
    ç¢į
    -0.08
    cro
    -0.08
    pres
    -0.08
    æĴĤ
    -0.08
     president
    -0.08
    åı°åĮĹ
    -0.08
    POSITIVE LOGITS
    æĹı
    0.10
    åĿ¨
    0.10
    æŶåħī
    0.10
    alysis
    0.09
    .bel
    0.09
     happy
    0.09
    happy
    0.09
    çĽĺ
    0.09
    NESS
    0.08
    ÑģÑĤвие
    0.08
    Activations Density 0.007%

    No Known Activations