© 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. 51908
    Prev
    Next
    INDEX
    Explanations

    to

    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
    /or
    -0.11
    nt
    -0.10
    ãģĦãģĨ
    -0.09
    айл
    -0.08
    ย
    -0.08
    дж
    -0.08
    ãģĦãģªãģĦ
    -0.08
    EDIA
    -0.08
    venture
    -0.08
    夫å¦ĩ
    -0.08
    POSITIVE LOGITS
    èĩ¾
    0.12
    åŃIJéĩĮ
    0.11
    .Unique
    0.09
    forth
    0.09
     gente
    0.09
    ence
    0.09
    çħ
    0.09
    amp
    0.09
    оÑĢ
    0.09
    ibration
    0.09
    Activations Density 0.011%

    No Known Activations