© 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. 52852
    Prev
    Next
    INDEX
    Explanations

    relationship between

    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
    æı¡
    -0.10
    ivre
    -0.09
    æĢģ
    -0.09
    -inline
    -0.09
    æ¦Ħ
    -0.08
    çľ©
    -0.08
     Subscribe
    -0.08
    abad
    -0.08
    utron
    -0.08
    绣ä¸Ģ
    -0.08
    POSITIVE LOGITS
    ç´§å¯Ĩ
    0.10
    æŃī
    0.10
    ï¸
    0.09
    èĭĴ
    0.09
    hell
    0.09
    STREAM
    0.09
    责任æĦŁ
    0.09
    sWith
    0.09
    家å±ħ
    0.08
    ain
    0.08
    Activations Density 0.023%

    No Known Activations