© 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. 21774
    Prev
    Next
    INDEX
    Explanations

    places to sleep or shelter

    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
    éĹ²
    -0.10
    åIJĥåĪ°
    -0.09
    æĥ³åİ»
    -0.09
    éĥ½è®¤ä¸º
    -0.09
    ä¸Ģ大æī¹
    -0.09
    çĪ±åIJĥ
    -0.08
    åĴ¦
    -0.08
    æĵİ
    -0.08
    æľīä¸Ģ次
    -0.08
    éĢīåĩº
    -0.08
    POSITIVE LOGITS
     couch
    0.10
    åºĬåŀ«
    0.10
     kê
    0.10
    åķĦ
    0.09
    åºĬä½į
    0.09
    .getLog
    0.09
    åŀ«
    0.09
     ngủ
    0.09
     sleeping
    0.09
    çĿ¡è§ī
    0.09
    Activations Density 0.054%

    No Known Activations