© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    opposite side

    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
    åŃ¦ä¹łæĪIJ绩
    -0.11
    责任æĦŁ
    -0.10
    iman
    -0.10
    æīĭåĨĮ
    -0.09
    akis
    -0.09
    bable
    -0.09
    ç»ŃèĪª
    -0.09
    rog
    -0.09
     Fle
    -0.09
    rado
    -0.09
    POSITIVE LOGITS
     opposite
    0.16
    缸åıį
    0.15
     Opp
    0.13
    éĺµèIJ¥
    0.12
    Opp
    0.11
    åı¦ä¸Ģè¾¹
    0.10
    /op
    0.10
     opposing
    0.10
    -side
    0.10
    Locator
    0.09
    Activations Density 0.036%

    No Known Activations