© 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. 5314
    Prev
    Next
    INDEX
    Explanations

    building and construction

    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
    åį°èĬ±
    -0.08
    çĸ¾
    -0.08
     termination
    -0.08
    isson
    -0.08
    åºĶæĶ¶
    -0.08
    _initializer
    -0.08
    çģ«çĦ°
    -0.08
    .sourceforge
    -0.08
    æĮ¨
    -0.08
    çĦ°
    -0.08
    POSITIVE LOGITS
    å·¥ç¨ĭ
    0.19
    建éĢł
    0.17
     engineering
    0.17
    å·¥ç¨ĭå¸Ī
    0.16
    æĸ½å·¥
    0.15
    å·¥ç¨ĭæĬĢæľ¯
    0.14
    engineering
    0.13
     Engineering
    0.13
    Engineering
    0.13
    å·¥ç¨ĭ建设
    0.13
    Activations Density 0.108%

    No Known Activations