© 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. 10115
    Prev
    Next
    INDEX
    Explanations

    vers or verse context

    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
    ARP
    -0.09
     лиÑĪÑĮ
    -0.09
    &#
    -0.08
    ssc
    -0.08
    iec
    -0.08
    ase
    -0.08
    ìĬ¹
    -0.08
    split
    -0.08
    衽
    -0.08
    cls
    -0.08
    POSITIVE LOGITS
    RIES
    0.11
    ailles
    0.11
    бÑĥ
    0.10
    YSTEM
    0.10
    atile
    0.10
    åĸĻ
    0.09
    ãģ¹ãģį
    0.09
    ries
    0.09
    ä¸ĩçī©
    0.09
    éļħ
    0.09
    Activations Density 0.018%

    No Known Activations