© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7781
    Prev
    Next
    INDEX
    Explanations

    examples of "factory", "based", "ford", "ard" endings

    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
    LEX
    -0.10
    utation
    -0.10
    itto
    -0.09
    uster
    -0.09
    imity
    -0.09
    enor
    -0.09
    urally
    -0.09
    ëĭĿ
    -0.09
    æīĵåĩ»
    -0.09
    andre
    -0.08
    POSITIVE LOGITS
    æĮŁ
    0.10
    ieres
    0.08
    hill
    0.08
    æł·çļĦ
    0.08
    ous
    0.08
    ugal
    0.08
    yyy
    0.08
    tin
    0.08
    åŃĽ
    0.08
    tw
    0.08
    Activations Density 0.005%

    No Known Activations