© 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. 47891
    Prev
    Next
    INDEX
    Explanations

    golden ratio or Fibonacci sequence

    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
    ä¸ī次
    -0.08
    çģĮ
    -0.08
    é¢Ħæ¡Ī
    -0.08
    å±ħ
    -0.08
    LIN
    -0.08
    CED
    -0.08
    éļıæľº
    -0.08
    ecn
    -0.08
    åIJĦæł·
    -0.08
    两次
    -0.08
    POSITIVE LOGITS
     Fibonacci
    0.11
    Golden
    0.11
    é»Ħéĩij
    0.10
     fibonacci
    0.10
    éªĬ
    0.10
    èĩªçĦ¶çķĮ
    0.10
     Fib
    0.10
     Golden
    0.09
    Trader
    0.09
    çªŁ
    0.09
    Activations Density 0.032%

    No Known Activations