© 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. 37380
    Prev
    Next
    INDEX
    Explanations

    acronyms for tools/software

    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
    IRQ
    -0.09
    åģļå·¥
    -0.09
    hood
    -0.09
    brand
    -0.09
    EAR
    -0.09
    dings
    -0.09
    ECT
    -0.09
    ä¿©
    -0.08
    EVER
    -0.08
    OrNil
    -0.08
    POSITIVE LOGITS
    人士
    0.11
    /OR
    0.10
    aaS
    0.10
    antas
    0.09
    'er
    0.09
    ï¸
    0.09
    æij½
    0.09
    çĴĺ
    0.09
    s
    0.09
    imensional
    0.08
    Activations Density 2.094%

    No Known Activations