© 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. 7335
    Prev
    Next
    INDEX
    Explanations

    intriguing stories

    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
    佬
    -0.10
    akah
    -0.09
    GES
    -0.09
    agan
    -0.09
    èħĶ
    -0.08
    ings
    -0.08
    č↵
    -0.08
    awan
    -0.08
    ë¡Ģ
    -0.08
    æĥħå½¢
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.13
    ly
    0.11
    ä¸įçĦ¶
    0.10
    åĬij
    0.10
    窿
    0.09
    è±¹
    0.09
    å·²ä¹ħ
    0.09
    ight
    0.09
    rey
    0.09
     Harden
    0.09
    Activations Density 0.005%

    No Known Activations