© 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. 20378
    Prev
    Next
    INDEX
    Explanations

    weapons

    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
    Ĩ
    -0.11
    uration
    -0.09
    人æ°ijæĶ¿åºľ
    -0.09
    OrCreate
    -0.08
    urre
    -0.08
    sing
    -0.08
    ingles
    -0.08
    ute
    -0.08
    åĽŀäºĭ
    -0.08
    ses
    -0.08
    POSITIVE LOGITS
    ized
    0.10
    mens
    0.09
    ะ
    0.09
    arium
    0.09
     lod
    0.08
    mith
    0.08
    å¤ł
    0.08
    åĦĴ
    0.08
    rete
    0.08
    -grade
    0.08
    Activations Density 0.013%

    No Known Activations