© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    pondering and contemplating

    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
    ually
    -0.09
    imulator
    -0.09
    ourcing
    -0.09
    ìķ¼
    -0.08
    ened
    -0.08
    ARP
    -0.08
    á»Ŀ
    -0.08
    owing
    -0.08
    олод
    -0.08
    olly
    -0.08
    POSITIVE LOGITS
    äºĨä¸Ģä¸ĭ
    0.10
    ohl
    0.09
    esh
    0.09
    éĹ·
    0.09
    è°´
    0.09
    çĿĢ
    0.09
    oso
    0.08
    åIJĮä»ģ
    0.08
    nts
    0.08
    edList
    0.08
    Activations Density 0.005%

    No Known Activations