© 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. 5947
    Prev
    Next
    INDEX
    Explanations

    know about

    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
     nick
    -0.08
    å°ij许
    -0.08
    çĶ¨æĪ·æıIJä¾Ľ
    -0.08
    åħ¨é¢Ŀ
    -0.08
    éĢĤ度
    -0.08
    å¯Įè´µ
    -0.08
    oine
    -0.08
    alom
    -0.08
    ean
    -0.08
    ä¸Ģå¤Ħ
    -0.07
    POSITIVE LOGITS
     about
    0.14
     tentang
    0.13
     vá»ģ
    0.12
     عÙĨÙĩا
    0.12
    åħ³äºİæĪij们
    0.12
    åħ³äºİ
    0.12
     عÙĨ
    0.12
     sobre
    0.11
    about
    0.11
    éĹľæĸ¼
    0.10
    Activations Density 0.040%

    No Known Activations