© 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. 50564
    Prev
    Next
    INDEX
    Explanations

    perspective and context

    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
    纯粹
    -0.11
    纯
    -0.09
    å°İ
    -0.09
     Quart
    -0.09
    ç´Ķ
    -0.09
    æµģ转
    -0.09
    导
    -0.08
    åħĨ
    -0.08
    سÙĪد
    -0.08
     Hear
    -0.08
    POSITIVE LOGITS
     context
    0.16
     perspective
    0.15
    context
    0.13
     Perspective
    0.13
    è§Ĩè§Ĵ
    0.12
    pers
    0.12
    (context
    0.11
    /context
    0.11
    	context
    0.11
     ctx
    0.11
    Activations Density 0.046%

    No Known Activations