© 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. 30755
    Prev
    Next
    INDEX
    Explanations

    merely or simply

    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
    plat
    -0.10
    cko
    -0.09
    åĿIJçĿĢ
    -0.09
    以人为
    -0.09
    æµij
    -0.09
    .isActive
    -0.09
    ç½Ħ
    -0.09
    åĶĨ
    -0.09
    _TIM
    -0.09
    rina
    -0.09
    POSITIVE LOGITS
     merely
    0.14
    èĢĮå·²
    0.13
    æŃ£å¸¸çļĦ
    0.13
    æĻ®éĢļçļĦ
    0.13
     simply
    0.13
    åģ¶å°Ķ
    0.12
    à¹ģà¸Ħ
    0.12
    æŃ£å¸¸
    0.11
     mere
    0.11
    åģ¶çĦ¶
    0.10
    Activations Density 0.224%

    No Known Activations