© 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. 3991
    Prev
    Next
    INDEX
    Explanations

    avi file extensions

    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
    æĭ®
    -0.09
    obl
    -0.09
    èĭĩ
    -0.08
    contra
    -0.08
    /mit
    -0.08
    statt
    -0.08
    å®ľ
    -0.08
    äºĮåįģäºĶ
    -0.08
    使ä¹ĭ
    -0.08
    ä½IJ
    -0.08
    POSITIVE LOGITS
    uat
    0.11
    å®Ĺ
    0.10
    lov
    0.10
    æľĽåİ»
    0.09
    OSE
    0.09
    igel
    0.08
    ATIC
    0.08
    æĥŃ
    0.08
    oes
    0.08
    ãĥijãĥ¼ãĥĪ
    0.08
    Activations Density 0.012%

    No Known Activations