© 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. 35830
    Prev
    Next
    INDEX
    Explanations

    experience

    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
    _DM
    -0.09
    æĸ¥
    -0.09
     Alban
    -0.09
    ift
    -0.09
    å¿«æīĭ
    -0.09
     Goodman
    -0.08
    温室
    -0.08
    é¸
    -0.08
    京津åĨĢ
    -0.08
    çĬ¹
    -0.08
    POSITIVE LOGITS
     exp
    0.13
    çķĻåѦ
    0.13
    å±ħä½ı
    0.11
    å¤ĸåĽ½
    0.11
    å¤ĸç±į
    0.10
    å¤ĸåĽ½äºº
    0.10
    çĶŁæ´»
    0.10
    æĬ¤çħ§
    0.10
     foreign
    0.09
    åĩºåħ¥å¢ĥ
    0.09
    Activations Density 0.202%

    No Known Activations