© 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. 17841
    Prev
    Next
    INDEX
    Explanations

    questions and explanations

    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
     dara
    -0.07
    éijij
    -0.06
    à¸Ńà¸ĩ
    -0.05
     broad
    -0.05
    游离
    -0.05
    å¹¿æ³Ľ
    -0.05
    为äºĨ让
    -0.05
    å¤ļæĥ³
    -0.05
     bomba
    -0.05
     retention
    -0.05
    POSITIVE LOGITS
    igo
    0.06
     registrati
    0.06
    å¥ı
    0.05
    omens
    0.05
    åįłåľ°
    0.05
    ú
    0.05
    计
    0.05
    appName
    0.05
    åĢ¾
    0.05
    åįĥç¯ĩ
    0.05
    Activations Density 0.001%

    No Known Activations