© 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. 55780
    Prev
    Next
    INDEX
    Explanations

    period followed by a word

    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
    reece
    -0.10
    è¾Ľåĭ¤
    -0.09
    imately
    -0.09
    æĿĸ
    -0.09
    iland
    -0.09
    å¥ĭ
    -0.09
    amera
    -0.09
    ĶĦ
    -0.09
    edException
    -0.09
    åīįçŀ»æĢ§
    -0.09
    POSITIVE LOGITS
    é»Ħéĩij
    0.08
    ä¿©
    0.08
    å¯Ħæīĺ
    0.08
    çĥģ
    0.08
     airl
    0.08
    æĭīåĬ¨
    0.07
    onor
    0.07
    ôi
    0.07
    çļĦçĶ·äºº
    0.07
    ذا
    0.07
    Activations Density 0.202%

    No Known Activations