© 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. 20861
    Prev
    Next
    INDEX
    Explanations

    trapped in

    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
    çĹ¢
    -0.10
    躬
    -0.09
    åħį责声æĺİ
    -0.09
    带åĽŀ
    -0.09
    åijĽ
    -0.09
    失踪
    -0.08
    isa
    -0.08
    ç¯Ļ
    -0.08
     Barker
    -0.08
    _MARKER
    -0.08
    POSITIVE LOGITS
    ä½ıäºĨ
    0.13
     trapped
    0.11
    PED
    0.11
    è¢«åĽ°
    0.10
    åĽ°
    0.09
    çªĺ
    0.09
    å±ĢéĻIJäºİ
    0.08
    åĽ¹
    0.08
    md
    0.08
    è¿Ľé¡¹
    0.08
    Activations Density 0.038%

    No Known Activations