© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    denominator, denomination, hemisphere

    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
    fone
    -0.10
    bucks
    -0.10
    éĺŁåijĺ们
    -0.09
    flix
    -0.09
    ome
    -0.09
    InOut
    -0.09
    ä¸įåħĭ
    -0.09
    iola
    -0.08
    imony
    -0.08
    ذر
    -0.08
    POSITIVE LOGITS
    ally
    0.11
    nal
    0.10
    ality
    0.10
    ä¸įéĻIJ
    0.09
    åĨħçļĦ
    0.09
    nos
    0.09
    æ®Ĩ
    0.09
    å¢ħ
    0.08
    -neutral
    0.08
    eral
    0.08
    Activations Density 0.006%

    No Known Activations