© 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. 50227
    Prev
    Next
    INDEX
    Explanations

    fluorescence detection or measurement

    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
    ä¹ĭåľ°
    -0.08
    èĬŁ
    -0.08
     amnesty
    -0.08
    导èĪª
    -0.08
    IntPtr
    -0.08
     Trot
    -0.08
    é¬Ĩ
    -0.07
    interp
    -0.07
    交ç»Ļ
    -0.07
    çŃīåľ°
    -0.07
    POSITIVE LOGITS
     Äijo
    0.10
    ç»ĪçĤ¹
    0.09
    measurement
    0.09
    鸳
    0.09
    åħ¬åĬ¡åijĺ
    0.09
    CADE
    0.09
    çĴ©
    0.09
     yên
    0.09
    ivent
    0.09
    éĹ
    0.09
    Activations Density 0.397%

    No Known Activations