© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21023
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
     cons
    -0.06
    urf
    -0.05
    ose
    -0.05
    andas
    -0.05
    åĩī
    -0.05
     âĶľâĶĢâĶĢ
    -0.05
     associ
    -0.05
    æĸĩ书
    -0.05
    link
    -0.05
    utter
    -0.05
    POSITIVE LOGITS
     Insomma
    0.06
    aker
    0.06
    å°ıç¼ĸ为大家æķ´çIJĨçļĦ
    0.06
    éĥ½å¿«
    0.06
    äººä¸ºæľ¬
    0.06
    以ä¸ĭæĿ¡ä»¶
    0.06
    两ç§įæĸ¹å¼ı
    0.06
    akest
    0.06
    é¦ĸå¸Ń
    0.05
    OperationException
    0.05
    Activations Density 0.001%

    No Known Activations