© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37261
    Prev
    Next
    INDEX
    Explanations

    manuals and constitutions

    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
    ä¸Ģç»Ħ
    -0.08
    åIJİèĢħ
    -0.08
    ä¿¡ç®±
    -0.08
    éĶ®
    -0.08
    åĨ²
    -0.08
    jaw
    -0.08
     redeemed
    -0.08
    linger
    -0.07
    å¤Ħ
    -0.07
    .EventQueue
    -0.07
    POSITIVE LOGITS
    èįīæ¡Ī
    0.13
    éĩĮçļĦ
    0.12
    åī¯æľ¬
    0.11
     Malk
    0.09
    对ä»ĸ们
    0.09
    å¤įåį°ä»¶
    0.09
    èµ°åĩºæĿ¥
    0.09
    à¸īà¸ļ
    0.09
    åĨħçļĦ
    0.09
    ä¸ŃåIJ«æľī
    0.09
    Activations Density 0.268%

    No Known Activations