© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36529
    Prev
    Next
    INDEX
    Explanations

    national, nationally + descriptor

    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
    çĵĺ
    -0.09
    obi
    -0.09
    æļ
    -0.08
    иде
    -0.08
    uet
    -0.08
    æľ¬åĽ½
    -0.08
    æ°ij
    -0.08
    åĪĽå§ĭ人
    -0.08
    ectomy
    -0.07
    inh
    -0.07
    POSITIVE LOGITS
    èĮĥåĽ´åĨħ
    0.14
    æĢ§çļĦ
    0.13
    /global
    0.13
    å±ĤéĿ¢
    0.12
    -wide
    0.12
    åĴĮåľ°åĮº
    0.11
    -level
    0.11
    /local
    0.11
    ized
    0.10
    -scale
    0.10
    Activations Density 0.056%

    No Known Activations