© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    talk radio

    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
    ality
    -0.12
    ÑģÑĮ
    -0.11
    äº¤æĽ¿
    -0.10
    eer
    -0.10
    ä¸įäºĨ
    -0.09
    iface
    -0.09
    èĭ¦èĭ¦
    -0.09
    efa
    -0.09
    MENT
    -0.09
    TING
    -0.09
    POSITIVE LOGITS
    ãģĬ話
    0.11
    ãģĬãģĦ
    0.10
    ships
    0.09
    geber
    0.09
    shops
    0.09
    heet
    0.09
    åĴĮåľ°åĮº
    0.09
    ero
    0.09
    ative
    0.09
    offs
    0.08
    Activations Density 0.027%

    No Known Activations