© 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. 37710
    Prev
    Next
    INDEX
    Explanations

    legislative action

    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
    iliar
    -0.10
    lege
    -0.09
    edin
    -0.09
    ish
    -0.09
    æĿľåħ°
    -0.09
    ingly
    -0.09
    lla
    -0.09
     leve
    -0.09
    stick
    -0.09
    çIJĨäºĭä¼ļ
    -0.08
    POSITIVE LOGITS
     cáºŃp
    0.09
    ãĤį
    0.09
    ocate
    0.09
    urally
    0.09
    åħ¶æ¬¡
    0.09
    оÑĢа
    0.09
    agan
    0.08
    дон
    0.08
    ically
    0.08
    opsy
    0.08
    Activations Density 0.006%

    No Known Activations