© 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. 49555
    Prev
    Next
    INDEX
    Explanations

    code punctuation or special characters

    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
    asio
    -0.10
    åį¯
    -0.08
    éĺħ读åħ¨æĸĩ
    -0.08
    伺æľį
    -0.08
    tle
    -0.08
    æij§
    -0.08
    jug
    -0.08
    filtr
    -0.08
    æł¹æľ¬ä¸į
    -0.08
    åħľ
    -0.08
    POSITIVE LOGITS
    ively
    0.12
    éķ¿è¾Ī
    0.10
    èĢĮåľ¨
    0.10
    éĥ
    0.09
    ï¸ı
    0.09
    天åłĤ
    0.09
    éĴ£
    0.09
    乡
    0.09
    éĺ¶
    0.09
    ether
    0.08
    Activations Density 0.079%

    No Known Activations