© 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. 63240
    Prev
    Next
    INDEX
    Explanations

    between two things

    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
    楣
    -0.11
    åĮł
    -0.11
    æ·¦
    -0.10
    ImageRelation
    -0.10
    åĵªæĢķæĺ¯
    -0.10
    ewise
    -0.09
    æĪijæīį
    -0.09
    åĵªæĢķ
    -0.09
    èĭĵ
    -0.09
    对åѦçĶŁ
    -0.09
    POSITIVE LOGITS
    ä»ĭ
    0.14
     between
    0.12
    ä¸ŃéĹ´
    0.11
     Between
    0.11
    ä¹ĭéĹ´
    0.10
     بÙĬÙĨ
    0.10
     междÑĥ
    0.10
     Intermediate
    0.09
    Between
    0.09
     giữa
    0.09
    Activations Density 0.050%

    No Known Activations