© 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. 56528
    Prev
    Next
    INDEX
    Explanations

    lithography

    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
    wife
    -0.10
    lify
    -0.09
    ình
    -0.09
    ĭ
    -0.09
    主ä¹īæĢĿæĥ³
    -0.09
    çĸļ
    -0.09
    ame
    -0.08
    ties
    -0.08
    hou
    -0.08
    nap
    -0.08
    POSITIVE LOGITS
    ues
    0.10
    ÙĨÙĬÙĨ
    0.10
    afen
    0.10
     Burnett
    0.09
    潦
    0.09
    gle
    0.09
    scopic
    0.09
    isches
    0.09
    urs
    0.09
    ically
    0.09
    Activations Density 0.064%

    No Known Activations