© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50585
    Prev
    Next
    INDEX
    Explanations

    OpenOCD, docker, stm32, ft2232

    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
    .ToTable
    -0.08
    ثر
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    trak
    -0.07
    _traits
    -0.07
    athom
    -0.07
    åIJİèĢħ
    -0.07
    ä½ĵçİ°åĩº
    -0.07
    ény
    -0.07
    .TabStop
    -0.07
    POSITIVE LOGITS
    è¿ĺä¸įå¦Ĥ
    0.08
    BUY
    0.08
    çĶļä¹Ī
    0.08
    ä¹Łå¥½
    0.08
    REFER
    0.08
    åĨįä¹Łæ²¡æľī
    0.07
    bai
    0.07
     Sapphire
    0.07
     Mey
    0.07
    _VF
    0.07
    Activations Density 1.947%

    No Known Activations