© 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. 51127
    Prev
    Next
    INDEX
    Explanations

    competition and conflict

    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
    .addTab
    -0.09
    èł¹
    -0.09
    åĪĴåĪĨ
    -0.09
    篾
    -0.09
    ä¼Ļ
    -0.09
    èĢģå¦Ī
    -0.08
    è±ķ
    -0.08
    .pivot
    -0.08
    ipse
    -0.08
    yleft
    -0.08
    POSITIVE LOGITS
    åīįä¸ī
    0.10
    èĨº
    0.10
    æ±
    0.09
    ze
    0.09
    æĢģåĬ¿
    0.09
    æīĵæĸŃ
    0.09
    äºī夺
    0.09
    æĬĵä½ı
    0.09
    çĭłæĬĵ
    0.09
    æĬ¼
    0.08
    Activations Density 0.045%

    No Known Activations