© 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. 31166
    Prev
    Next
    INDEX
    Explanations

    automatic safety locks and timers

    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
    osi
    -0.10
    èĭįçĻ½
    -0.10
    çĭ¸
    -0.09
    æĮijè¡ħ
    -0.09
    ENTRY
    -0.09
    æĢ§ä»·
    -0.09
    rlen
    -0.09
    ä¸ĢåĽ¢
    -0.09
    ific
    -0.08
    usi
    -0.08
    POSITIVE LOGITS
    èĩªåĬ¨
    0.12
    åĢĴ
    0.11
     automatic
    0.10
    éĶģå®ļ
    0.10
    automatic
    0.09
     automatically
    0.09
     locking
    0.09
    æľºåĪ¶
    0.09
    -stop
    0.08
    å®ģ
    0.08
    Activations Density 0.192%

    No Known Activations