© 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. 35580
    Prev
    Next
    INDEX
    Explanations

    lysosomal pathways

    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
    èijŃ
    -0.10
    å±ŀäºİèĩªå·±
    -0.10
    äºĴåĬ©
    -0.10
    å·¦æīĭ
    -0.09
    eners
    -0.09
    ä½°
    -0.09
    太æŀģ
    -0.09
    ä¿Ĺ
    -0.09
    _inst
    -0.09
    漫éķ¿
    -0.09
    POSITIVE LOGITS
    ÙĤÙĩ
    0.10
     pinch
    0.10
    åĨħå¤ĸ
    0.09
    èĮ¶
    0.09
    rocessing
    0.08
    ikk
    0.08
    æ¹¾åĮº
    0.08
    oves
    0.08
    éĢĢè´§
    0.08
    åłµ
    0.08
    Activations Density 0.424%

    No Known Activations