© 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. 20997
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
    aly
    -0.07
    aby
    -0.06
    figur
    -0.05
    iffs
    -0.05
    çİĩçļĦ
    -0.05
    amen
    -0.05
    à¸Ńยà¹Īาà¸ĩยิà¹Īà¸ĩ
    -0.05
    าà¸Ĺี
    -0.05
    çİĩåĴĮ
    -0.05
    éĬ
    -0.05
    POSITIVE LOGITS
    oft
    0.07
    ingend
    0.07
    alak
    0.06
    好å¤Ħ
    0.06
    obot
    0.06
    generation
    0.06
     Intelli
    0.06
    ungsi
    0.06
    outh
    0.06
    Äijá»ĥ
    0.06
    Activations Density 0.004%

    No Known Activations