© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    give you an idea or feeling

    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
    илÑĮно
    -0.10
    åIJ»
    -0.09
    è¾ħ导
    -0.09
    .Root
    -0.09
    OME
    -0.09
    æĺİæĺİ
    -0.08
    çĻ½æ²Ļ
    -0.08
    åij½
    -0.08
    ç²¾å¿ĥ
    -0.08
    çijĻ
    -0.08
    POSITIVE LOGITS
    åį°è±¡
    0.12
    äºĨ解
    0.11
    大èĩ´
    0.10
    大家
    0.10
     sense
    0.10
    çŀŃ解
    0.10
    æĥ³æ³ķ
    0.10
    èµı
    0.10
     idea
    0.09
    çļĦåį°è±¡
    0.09
    Activations Density 0.037%

    No Known Activations