© 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. 7583
    Prev
    Next
    INDEX
    Explanations

    island and island groups

    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
    æIJŃ
    -0.10
    å¹³åİŁ
    -0.10
    енÑĤа
    -0.10
    ActionBar
    -0.09
    éĶĦ
    -0.09
     tap
    -0.09
    é¦Ĵ头
    -0.09
    çī½
    -0.09
    çīµ
    -0.09
    åĪ¹éĤ£
    -0.09
    POSITIVE LOGITS
    ç¾¤å²Ľ
    0.17
    å²Ľä¸Ĭ
    0.17
    å²Ľ
    0.16
     Islands
    0.15
    æµ·å²Ľ
    0.15
     island
    0.14
     islands
    0.13
    å²Ľå±¿
    0.13
     Äijảo
    0.13
    島
    0.13
    Activations Density 0.116%

    No Known Activations