© 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. 30292
    Prev
    Next
    INDEX
    Explanations

    scholarship, fellowship, funded studies

    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
    abay
    -0.10
    å¾µ
    -0.09
    å³»
    -0.09
    顾
    -0.08
    çī
    -0.08
     Gavin
    -0.08
    iring
    -0.08
    峡
    -0.08
    _SOC
    -0.08
    ousy
    -0.08
    POSITIVE LOGITS
    èµ´
    0.14
    åĩºåĽ½
    0.13
    çķĻåѦ
    0.13
    å¥ĸåѦéĩij
    0.11
    åĩºåĽ½çķĻåѦ
    0.10
     Tu
    0.10
     abroad
    0.10
    饯
    0.10
     scholarships
    0.10
    tu
    0.10
    Activations Density 0.085%

    No Known Activations