© 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. 36863
    Prev
    Next
    INDEX
    Explanations

    [proper noun] of

    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
    ous
    -0.08
    inh
    -0.08
    楼æĪ¿
    -0.08
    less
    -0.08
    åħ¶
    -0.08
    tin
    -0.08
    è£Ķ
    -0.07
    infer
    -0.07
    åºĶæľīçļĦ
    -0.07
    asha
    -0.07
    POSITIVE LOGITS
    /from
    0.12
    thon
    0.10
    /of
    0.10
    ften
    0.09
    _PCM
    0.09
    åĩ¡äºĭ
    0.09
    ç½ijå°ıç¼ĸ
    0.09
    annon
    0.09
    icina
    0.09
    /on
    0.09
    Activations Density 0.250%

    No Known Activations