© 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. 22191
    Prev
    Next
    INDEX
    Explanations

    individual users, retail outlets, many people, experts

    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
    åĿĽ
    -0.10
     Gad
    -0.09
    imore
    -0.09
    楼ä¸Ĭ
    -0.09
    _packages
    -0.08
    éĢĤ度
    -0.08
    .asm
    -0.08
    èµ´
    -0.08
    为äºĨ让
    -0.08
    大家ä¸Ģèµ·
    -0.08
    POSITIVE LOGITS
    æĶ¿åºľéĩĩè´Ń
    0.14
    à¸Ļำà¹Ħà¸Ľ
    0.13
     Bulk
    0.10
    åıįé¦Ī
    0.10
    éĩĩè´Ń
    0.09
    ç¾¹
    0.09
    åįij
    0.09
    åĪĩåħ¥
    0.09
     bulk
    0.09
    æĮijåīĶ
    0.09
    Activations Density 0.172%

    No Known Activations