© 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. 50855
    Prev
    Next
    INDEX
    Explanations

    writing or continuation

    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
    ype
    -0.09
    ments
    -0.09
    èİĵ
    -0.09
    -phase
    -0.08
    melon
    -0.08
    inkel
    -0.08
    5
    -0.08
    7
    -0.08
     kok
    -0.08
    0
    -0.08
    POSITIVE LOGITS
    er
    0.13
    erk
    0.09
    .AppSettings
    0.09
    è¶Ĭæĺ¯
    0.08
    åħ³éĶ®æĺ¯
    0.08
    è¨ĢãģĪãģ°
    0.08
    ä¸¥æł¼çļĦ
    0.08
    /free
    0.08
    èīºæľ¯åĵģ
    0.08
    UNET
    0.08
    Activations Density 0.073%

    No Known Activations