© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9017
    Prev
    Next
    INDEX
    Explanations

    bodily, bodom, bodmin, bodmin, bodip, bodr, bodle, boddy, bodys, bodh

    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
    ingly
    -0.10
    aging
    -0.10
    lining
    -0.08
    erre
    -0.08
    egin
    -0.08
    LEC
    -0.08
    俾
    -0.08
    oure
    -0.08
    fort
    -0.08
    æŃĩ
    -0.08
    POSITIVE LOGITS
    rees
    0.10
     Merkel
    0.09
    ysize
    0.09
    æĨ¬
    0.09
    éŃĦ
    0.09
    è§İ
    0.09
    зав
    0.08
    åĵĴ
    0.08
    ules
    0.08
    ities
    0.08
    Activations Density 0.018%

    No Known Activations