© 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. 53198
    Prev
    Next
    INDEX
    Explanations

    turbo, aspiration, compressor

    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
    ÑĨов
    -0.09
    alink
    -0.09
    åľ¨æ·±åľ³
    -0.09
    大大å°ı
    -0.09
    è¯ģ
    -0.09
     Wer
    -0.09
    åĮĻ
    -0.09
    æĬķ
    -0.09
    éľĩ
    -0.09
    aData
    -0.09
    POSITIVE LOGITS
    éĹ®åĢĻ
    0.10
    è¿«
    0.10
    èĻ
    0.10
    åĻ¨
    0.09
    ä»ĭ
    0.09
    2
    0.08
    æķĪåĬĽ
    0.08
    0
    0.08
    6
    0.08
     salvage
    0.08
    Activations Density 0.053%

    No Known Activations