© 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. 30468
    Prev
    Next
    INDEX
    Explanations

    can redistribute or obtain

    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
    èĥ½å¾ĹåĪ°
    -0.13
    èĥ½å¤Ł
    -0.12
    èĥ½è¾¾åĪ°
    -0.11
    èĥ½å¤Łè®©
    -0.11
    éģĩåĪ°äºĨ
    -0.10
    å¼ĢåIJ¯äºĨ
    -0.10
    èĥ½å¤ł
    -0.10
    è¿Ļæīį
    -0.10
    تاب
    -0.10
    å¤ļåįĬ
    -0.10
    POSITIVE LOGITS
    't
    0.18
    ’t
    0.17
    /w
    0.17
    -être
    0.16
    berra
    0.14
    tered
    0.13
    onical
    0.13
    ä¹ŁåºĶ该
    0.13
    åģļåĪ°
    0.13
    /do
    0.12
    Activations Density 0.294%

    No Known Activations