© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62851
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ly' or starting with 'Ly'

    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
    zilla
    -0.10
     лÑĥÑĩ
    -0.10
    itious
    -0.10
    ราà¸Ĭ
    -0.09
    iro
    -0.09
    ../
    -0.09
    sWith
    -0.09
    reet
    -0.09
    pees
    -0.09
    uation
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.11
    代表大ä¼ļ
    0.10
    icode
    0.09
    ings
    0.09
    ãģĹãģ¾ãģĦ
    0.09
    otropic
    0.09
    ifax
    0.09
    ç¬Ĩ
    0.09
    åĥ¹
    0.09
    sonian
    0.09
    Activations Density 0.035%

    No Known Activations