© 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. 37129
    Prev
    Next
    INDEX
    Explanations

    few followed by noun

    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
    累累
    -0.09
    æ»Ķ
    -0.08
    finite
    -0.08
    åı¦ä¸Ģä½į
    -0.08
    Scan
    -0.08
    æŁ³
    -0.08
    aded
    -0.08
    adel
    -0.08
    .ind
    -0.08
     _$
    -0.08
    POSITIVE LOGITS
    theless
    0.12
     à¹Ĩ
    0.12
    est
    0.11
    /no
    0.11
    ÑĪей
    0.11
    ened
    0.11
    à¹Ĩ
    0.10
    åľ°æĸ¹
    0.10
    lessly
    0.10
    möglich
    0.10
    Activations Density 0.019%

    No Known Activations