© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37291
    Prev
    Next
    INDEX
    Explanations

    objective-c method signatures

    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
    äºĺ
    -0.09
    ception
    -0.09
    onium
    -0.09
    ÑģмоÑĤÑĢ
    -0.08
    ed
    -0.08
    alus
    -0.08
    elijk
    -0.08
     вÑģем
    -0.08
    ening
    -0.08
    ноÑģÑĤ
    -0.08
    POSITIVE LOGITS
    åºĬä¸Ĭ
    0.10
    -ending
    0.09
    udge
    0.09
    裳
    0.09
    sek
    0.09
    ught
    0.09
    çĵ£
    0.08
    ä¸į解
    0.08
    åIJĮåŁİ
    0.08
    帻
    0.08
    Activations Density 0.245%

    No Known Activations