© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38482
    Prev
    Next
    INDEX
    Explanations

    remember or recognise something/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
    temps
    -0.09
    å®īåħ¨ä¿Ŀéļľ
    -0.09
    èŁł
    -0.09
    绾
    -0.08
     bore
    -0.08
    åĨ·æ°´
    -0.08
    æ´µ
    -0.08
    絡
    -0.08
    çĨ¬
    -0.08
    治好
    -0.08
    POSITIVE LOGITS
    ç¼ħ
    0.12
    åıįæĢĿ
    0.12
    æĢĿèĢĥ
    0.11
    è°¨
    0.10
    纪念
    0.10
    é»ĺ
    0.10
     pause
    0.10
    æĢĿ念
    0.09
    æĦŁ
    0.09
    çŀ»
    0.09
    Activations Density 0.096%

    No Known Activations