© 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. 1342
    Prev
    Next
    INDEX
    Explanations

    optional options

    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
    antine
    -0.09
    inand
    -0.09
    驶
    -0.09
    round
    -0.08
    æ¼ı
    -0.08
    /avatar
    -0.08
    ppard
    -0.08
    ActionButton
    -0.08
    irma
    -0.08
    .Restr
    -0.08
    POSITIVE LOGITS
    optional
    0.14
     optional
    0.14
    (Optional
    0.12
     opc
    0.12
    Optional
    0.12
     OPTIONAL
    0.12
     Optional
    0.11
    	Optional
    0.11
    OPTION
    0.11
    (optional
    0.11
    Activations Density 0.055%

    No Known Activations