© 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. 9233
    Prev
    Next
    INDEX
    Explanations

    prophet or prophecy

    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
    CriticalSection
    -0.10
    æķijæĬ¤
    -0.09
    uration
    -0.09
     phép
    -0.09
    OfString
    -0.09
    æĶĢçĻ»
    -0.08
    emp
    -0.08
    agn
    -0.08
    驹
    -0.08
     Aware
    -0.08
    POSITIVE LOGITS
    ical
    0.10
    ically
    0.10
    ess
    0.10
    ively
    0.10
    eur
    0.10
    ional
    0.10
    磧
    0.09
    idis
    0.09
    è¡«
    0.09
    è¢į
    0.09
    Activations Density 0.009%

    No Known Activations