© 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. 4832
    Prev
    Next
    INDEX
    Explanations

    investigating into

    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
    对çħ§æ£ĢæŁ¥
    -0.10
    æĥ³åĪ°äºĨ
    -0.09
    лов
    -0.09
    à¸Īาà¸ģà¸ģาร
    -0.09
    stry
    -0.09
    å¿ĥæĥħ
    -0.08
    ities
    -0.08
    lessly
    -0.08
    ั
    -0.08
    ç¨Ģ
    -0.08
    POSITIVE LOGITS
    å¹½
    0.11
    fen
    0.10
    rig
    0.09
    ä¸Ģçķª
    0.09
    æł¸å®ŀ
    0.09
    _into
    0.09
    æ¶ķ
    0.08
     اÙĦØ£Ùħر
    0.08
     into
    0.08
    áŀİ
    0.08
    Activations Density 0.049%

    No Known Activations