© 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. 51928
    Prev
    Next
    INDEX
    Explanations

    interview with

    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
    icator
    -0.09
    occo
    -0.09
    æĬ¤èº«
    -0.09
    çī¹åĪ«å£°æĺİ
    -0.08
    adores
    -0.08
    ador
    -0.08
    åĿļ硬
    -0.08
    æĪijèĥ½
    -0.08
    æĪijè¿ĺ
    -0.08
    åľ¨ä»ĸ
    -0.08
    POSITIVE LOGITS
    qua
    0.11
    .mods
    0.10
    ioni
    0.10
     владелÑĮ
    0.09
    èĢĺ
    0.09
    ä½ľèĢħæľ¬äºº
    0.08
    Iso
    0.08
    æĺĶæĹ¥
    0.08
     fab
    0.08
    _iso
    0.08
    Activations Density 0.027%

    No Known Activations