© 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. 38557
    Prev
    Next
    INDEX
    Explanations

    hoping for something or someone

    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
    äºĨ许å¤ļ
    -0.11
     Ñģобой
    -0.09
    atz
    -0.09
    è¾Ĩ车
    -0.09
    .GetData
    -0.09
    æīįå¹²
    -0.09
    Ñģла
    -0.09
    ä¹ĭæīĢ
    -0.09
    sWith
    -0.09
    agues
    -0.09
    POSITIVE LOGITS
    rd
    0.10
     spect
    0.08
    ilen
    0.08
    çī¹æľīçļĦ
    0.08
    çģ°èī²
    0.08
    ä¸ĭä¸Ģ个
    0.08
    æį·
    0.07
    anson
    0.07
    æĺ§
    0.07
    ä¸ĢæĿ¡
    0.07
    Activations Density 0.021%

    No Known Activations