© 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. 48365
    Prev
    Next
    INDEX
    Explanations

    information

    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
    utes
    -0.10
    ial
    -0.09
    unes
    -0.09
    Ñģол
    -0.08
    çī¹æ®Ĭ
    -0.08
    elson
    -0.08
     Pang
    -0.08
    åļ
    -0.08
    ä¸įæŃ»
    -0.08
    é£ĺ
    -0.08
    POSITIVE LOGITS
    åĴĮæĶ¯æĮģ
    0.11
     about
    0.10
    ç»ıå¼Ģ
    0.09
    èĪ«
    0.09
    å®ĺ
    0.09
    çĶŁäº§åĴĮ
    0.09
     tentang
    0.09
    åįģå¹´åīį
    0.09
    finity
    0.09
    .Master
    0.09
    Activations Density 0.050%

    No Known Activations