© 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. 22982
    Prev
    Next
    INDEX
    Explanations

    day, day-to-day

    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
    edm
    -0.10
    åľ¨åĨħçļĦ
    -0.10
    elly
    -0.10
    	Con
    -0.10
    ICA
    -0.09
    enthal
    -0.09
    incinn
    -0.09
    undy
    -0.09
    mdi
    -0.09
    ible
    -0.09
    POSITIVE LOGITS
    dream
    0.14
     ÑĢождениÑı
    0.09
    OfWeek
    0.09
    tech
    0.09
    iscal
    0.09
    iful
    0.09
    time
    0.09
    åŃIJéĩĮ
    0.09
    fair
    0.09
    ter
    0.09
    Activations Density 0.051%

    No Known Activations