© 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. 4942
    Prev
    Next
    INDEX
    Explanations

    foreign character sequences

    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
    æĢ»ä¹ĭ
    -0.09
    è±¹
    -0.09
    åľ¨èģĮ
    -0.08
     gest
    -0.08
    ä¸į足以
    -0.08
    meg
    -0.08
    etur
    -0.08
    åĨı
    -0.08
    heet
    -0.08
    cores
    -0.08
    POSITIVE LOGITS
    roach
    0.10
    _MANY
    0.10
    åŁł
    0.09
    หมาย
    0.09
    ropdown
    0.09
    éĤĪ
    0.09
    æĦļ
    0.09
    wner
    0.09
    çĵ®
    0.09
    æĭħ
    0.08
    Activations Density 0.098%

    No Known Activations