© 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. 9917
    Prev
    Next
    INDEX
    Explanations

    Tampa Bay, responsible for

    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
    /support
    -0.08
    ä½łè¿ĺ
    -0.08
    HEAD
    -0.08
    æľīåĪ©äºİ
    -0.08
    LayoutManager
    -0.07
    夬
    -0.07
    edo
    -0.07
    _LOOKUP
    -0.07
    clc
    -0.07
    åŃ¦ä¹łæĪIJ绩
    -0.07
    POSITIVE LOGITS
    æ®Ĩ
    0.10
    çĹī
    0.10
    æīĭç»Ń
    0.09
    _MISC
    0.09
    _scalar
    0.09
    _BOUNDS
    0.09
    æ¸Ĭ
    0.09
    饯
    0.09
    ç¼ł
    0.09
    éľĦ
    0.09
    Activations Density 0.002%

    No Known Activations