© 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. 50826
    Prev
    Next
    INDEX
    Explanations

    by the

    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
     formally
    -0.09
    Tick
    -0.09
    ç²ī
    -0.08
    æµģæ°´
    -0.08
    å¤ļå°ij
    -0.08
     Tick
    -0.08
    æł·åŃIJ
    -0.08
    ãģĻãģ¹
    -0.08
    åĶ§
    -0.08
    èĬ±æł·
    -0.08
    POSITIVE LOGITS
    èij¡èIJĦ
    0.10
    æĬĵä½ı
    0.10
    IZER
    0.09
    è¦ģçĤ¹
    0.09
    缩çŁŃ
    0.09
    æĬĬæı¡
    0.09
     grasp
    0.09
    çIJµ
    0.09
    认è¯Ĩ
    0.09
    Cold
    0.08
    Activations Density 0.034%

    No Known Activations