© 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. 34681
    Prev
    Next
    INDEX
    Explanations

    prove or proving

    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
    apult
    -0.09
    éħĭ
    -0.09
     пÑĢог
    -0.09
    æĮĩå¼ķ
    -0.09
    å§Ĩ
    -0.08
    åĩŃä»Ģä¹Ī
    -0.08
    åij£
    -0.08
    inja
    -0.08
     Revel
    -0.08
     ÑĢеалÑĮно
    -0.08
    POSITIVE LOGITS
    æĻ°
    0.18
    ä¸įäºĨ
    0.12
    ably
    0.11
    edores
    0.11
    å¾Ĵ
    0.10
    è¿Ļä¸ĢçĤ¹
    0.10
    缱
    0.10
    大家éĥ½åľ¨
    0.09
    ance
    0.09
    iate
    0.09
    Activations Density 0.039%

    No Known Activations