© 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. 21598
    Prev
    Next
    INDEX
    Explanations

    tuscan, tuskegee, tusculum, tusks

    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
    son
    -0.09
    çİĭåŃIJ
    -0.08
    ÑģÑĤавил
    -0.08
    çĬĬ
    -0.08
    EMPL
    -0.08
    åĦ¿å¥³
    -0.08
    sters
    -0.08
    ko
    -0.08
    主管
    -0.08
    ulus
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.10
    weed
    0.10
    ç¢į
    0.09
    owl
    0.09
    antly
    0.09
    æ®ĥ
    0.09
    croft
    0.09
     Soros
    0.09
    è¿Ľç¨ĭ
    0.08
    _CLI
    0.08
    Activations Density 0.006%

    No Known Activations