© 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. 53148
    Prev
    Next
    INDEX
    Explanations

    immediately followed by

    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
    manship
    -0.11
    oot
    -0.10
    weise
    -0.10
    ½
    -0.10
    lify
    -0.09
    eros
    -0.09
    ning
    -0.09
    ç²¹
    -0.09
    åĦ¿
    -0.09
    pus
    -0.09
    POSITIVE LOGITS
    iator
    0.10
    emente
    0.10
    aneously
    0.10
    iating
    0.10
    iation
    0.10
    aneous
    0.10
    zelf
    0.09
     vicinity
    0.09
    yah
    0.09
    æĥ³ä¸įåĪ°
    0.09
    Activations Density 0.011%

    No Known Activations