© 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. 34391
    Prev
    Next
    INDEX
    Explanations

    Galileo system, Euclidean distance

    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
    羯
    -0.10
     sø
    -0.09
    inux
    -0.09
    ached
    -0.08
     Turk
    -0.08
    à¹ģà¸Ħ
    -0.08
    cobra
    -0.08
     hawk
    -0.08
    heim
    -0.08
     Valk
    -0.08
    POSITIVE LOGITS
    çĸĻ
    0.10
    è±ģ
    0.10
    æ´İ
    0.10
    åĶ¾
    0.09
    çķĪ
    0.09
    ibs
    0.09
    shi
    0.09
    èħ±
    0.08
    åħ³
    0.08
    åİĦ
    0.08
    Activations Density 0.010%

    No Known Activations