© 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. 2264
    Prev
    Next
    INDEX
    Explanations

    profitability and financial gain

    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
    åħ¨æĹ¥åĪ¶
    -0.09
    enced
    -0.09
     nét
    -0.08
    istic
    -0.08
    åĴĦ
    -0.08
    å¥Ħ
    -0.08
    çĵĴ
    -0.08
    icap
    -0.08
    etur
    -0.08
    mos
    -0.08
    POSITIVE LOGITS
    殿ä¸ĭ
    0.11
     nhuáºŃn
    0.10
    æĹłæ¯Ķ
    0.10
    éĻĽ
    0.10
    ä¸ĢéĿ¢
    0.10
    åģ¥åº·çļĦ
    0.10
    è¿Ħ
    0.09
    ç»ıèIJ¥èĢħ
    0.09
    ting
    0.09
    æľīæĦıæĢĿçļĦ
    0.09
    Activations Density 0.005%

    No Known Activations