© 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. 49591
    Prev
    Next
    INDEX
    Explanations

    installation monitoring

    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
    æ¡Ĩæŀ¶
    -0.10
    åĨ²åĩ»
    -0.09
    èµ·éĩį
    -0.09
     landing
    -0.09
    æĭĪ
    -0.09
    èĤĭ
    -0.08
    åĽŀåĪ°
    -0.08
    æľºåºĬ
    -0.08
    åĽŀåĪ°äºĨ
    -0.08
    åľŁ
    -0.08
    POSITIVE LOGITS
    æĬ¥èѦ
    0.13
    å®īè£ħ
    0.13
    æ²»å®ī
    0.12
     installation
    0.10
     ìĦ¤ì¹ĺ
    0.10
    éĹªçĥģ
    0.10
    èѦ
    0.10
    ä¸ĩçī©
    0.09
    åĵ¨
    0.09
    ترÙĥÙĬب
    0.09
    Activations Density 0.236%

    No Known Activations