© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37203
    Prev
    Next
    INDEX
    Explanations

    localhost or 127.0.0.1 IP addresses

    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
    ued
    -0.10
     Ging
    -0.10
    åľ¨åºĬä¸Ĭ
    -0.10
    atoire
    -0.09
    intree
    -0.09
    年代
    -0.09
    UED
    -0.09
     misunder
    -0.09
    quisition
    -0.09
    _managed
    -0.09
    POSITIVE LOGITS
    =localhost
    0.10
     reachable
    0.10
     localhost
    0.10
    ç½Ķ
    0.09
     tattoo
    0.09
    æĺ¯åĽ½åĨħ
    0.08
     newly
    0.08
     yı
    0.08
    ibel
    0.08
    localhost
    0.08
    Activations Density 0.376%

    No Known Activations