© 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. 35679
    Prev
    Next
    INDEX
    Explanations

    island or islands

    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
    Ev
    -0.11
    赶
    -0.10
    _ev
    -0.10
     ev
    -0.09
    æ´½
    -0.09
    èİĵ
    -0.09
    çģ«åĬĽ
    -0.09
    иÑĢÑĥ
    -0.09
     stall
    -0.08
    å¨ģ
    -0.08
    POSITIVE LOGITS
    å¡ŀ
    0.12
     islands
    0.12
     moons
    0.11
    å²Ľå±¿
    0.11
     Islands
    0.10
    ç«ŀäºī对æīĭ
    0.10
    สะ
    0.10
    æŀķ
    0.10
    天çĦ¶
    0.09
    æľªæĪIJ
    0.09
    Activations Density 0.061%

    No Known Activations