© 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. 22644
    Prev
    Next
    INDEX
    Explanations

    Jefferson associated with places

    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
    ulative
    -0.09
    ison
    -0.09
     mẽ
    -0.09
    æ½¢
    -0.08
    女è£ħ
    -0.08
    kes
    -0.08
    åģļå·¥
    -0.08
    éªĸ
    -0.08
    èĥ¸åı£
    -0.08
    ivil
    -0.08
    POSITIVE LOGITS
    nant
    0.11
    naire
    0.11
    nal
    0.10
    nement
    0.10
    çªį
    0.10
    ripper
    0.10
    alia
    0.10
    oids
    0.09
    æ¶ķ
    0.09
    cko
    0.09
    Activations Density 0.011%

    No Known Activations