© 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. 50644
    Prev
    Next
    INDEX
    Explanations

    naturalization citizenship

    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
    åıł
    -0.10
    俸
    -0.10
    éĵľ
    -0.09
     evac
    -0.09
    porto
    -0.09
    åıijåĩº
    -0.09
    quine
    -0.09
     Goa
    -0.09
    @d
    -0.09
    主宰
    -0.09
    POSITIVE LOGITS
    åħ¥åħļ
    0.18
    çĶ³è¯·
    0.12
    çļĪ
    0.12
     baptism
    0.12
     conversion
    0.11
    èľķåıĺ
    0.11
    mint
    0.11
    çĶ³è«ĭ
    0.10
    åĽ½ç±į
    0.10
    æĺĦ
    0.10
    Activations Density 0.037%

    No Known Activations