© 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. 8628
    Prev
    Next
    INDEX
    Explanations

    solar system components

    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
    ãĥ³ãĤ°
    -0.10
    urre
    -0.10
    enant
    -0.10
    èĸ®
    -0.09
    ****************************************************************************
    -0.09
    ä¸ļ
    -0.09
    gle
    -0.09
    elan
    -0.09
    ðŁı»
    -0.09
    зеÑĢ
    -0.08
    POSITIVE LOGITS
    ium
    0.15
    thon
    0.13
    ized
    0.12
    ìį¨
    0.11
    âĺĢ
    0.10
    flare
    0.10
    åĺĺ
    0.10
    è¿ĺ好
    0.09
    burst
    0.09
    ken
    0.09
    Activations Density 0.011%

    No Known Activations