© 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. 3516
    Prev
    Next
    INDEX
    Explanations

    you under

    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
    caps
    -0.09
    /apis
    -0.09
    å®Ĺ
    -0.09
    å®ĹæŨ
    -0.09
    nim
    -0.09
    orest
    -0.08
    ulle
    -0.08
    ṡ
    -0.08
    以ä¸ĬåѦåİĨ
    -0.08
    /install
    -0.08
    POSITIVE LOGITS
    å´©
    0.10
    èİ
    0.10
    aurus
    0.09
     Hugo
    0.09
    èĪĮå°ĸ
    0.09
    ç¥
    0.09
    æľ¬å¸Ĥ
    0.09
    avigate
    0.09
    ering
    0.09
    åįģ大
    0.08
    Activations Density 0.003%

    No Known Activations