© 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. 18614
    Prev
    Next
    INDEX
    Explanations

    light and illumination

    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
    æ¸ħè¿ľ
    -0.09
    å¼ķçĪĨ
    -0.08
    å·§
    -0.08
     çık
    -0.08
    è²¼
    -0.08
    é«ĺä½İ
    -0.08
    æ¸ħåĩĢ
    -0.08
    çĩĥ
    -0.08
    æij¸
    -0.08
    åĩºåĶ®
    -0.08
    POSITIVE LOGITS
    åħī线
    0.16
    åħīçħ§
    0.13
    çģ¯åħī
    0.12
     light
    0.11
    å°Ħ
    0.11
    åħīèĬĴ
    0.11
    éĺ³åħī
    0.11
     sunlight
    0.10
    light
    0.10
     lighting
    0.10
    Activations Density 0.098%

    No Known Activations