© 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. 53802
    Prev
    Next
    INDEX
    Explanations

    passage of time

    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
    æĹ©æĹ©
    -0.10
    çĦĸ
    -0.10
    ç½¢
    -0.09
    æģ¶éŃĶ
    -0.09
    èı²
    -0.09
    <TKey
    -0.09
    ä»ĸå¦Ī
    -0.09
     nineteenth
    -0.09
    æĹ©æľŁ
    -0.09
    æīĵå¾Ĺ
    -0.09
    POSITIVE LOGITS
    å²ģæľĪ
    0.13
    åħīéĺ´
    0.13
    æµģéĢĿ
    0.13
     time
    0.12
    æŶåħī
    0.12
     elapsed
    0.12
    æŶéĹ´
    0.11
    è¿ĩåİ»äºĨ
    0.11
    æĻĤéĸĵãģĮ
    0.11
    Elapsed
    0.11
    Activations Density 0.040%

    No Known Activations