© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9393
    Prev
    Next
    INDEX
    Explanations

    Javascript is disabled

    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
    Survey
    -0.10
    æģ¯
    -0.10
    èĤ¡ä¸ľ
    -0.09
    æį§
    -0.09
    /configuration
    -0.09
    饿
    -0.09
    åĩłå®¶
    -0.09
    æĹłå£°
    -0.08
    妻
    -0.08
    _KP
    -0.08
    POSITIVE LOGITS
    curities
    0.09
    arked
    0.09
    æĪIJ交éĩı
    0.09
    黳
    0.08
    _RESOURCES
    0.08
    ath
    0.08
    è¾ĥå¿«
    0.08
    eren
    0.08
    asa
    0.08
    å¿
    0.08
    Activations Density 0.057%

    No Known Activations