© 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. 21558
    Prev
    Next
    INDEX
    Explanations

    obeying rules and complying

    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
    ing
    -0.07
    æ±Ĥ解
    -0.05
    dress
    -0.05
     Germ
    -0.05
    alet
    -0.05
    СÐļÐIJ
    -0.05
    ิà¹īà¸ĩ
    -0.05
    еÑī
    -0.05
    ersch
    -0.05
    eschi
    -0.05
    POSITIVE LOGITS
    ادر
    0.07
    ation
    0.06
    åĽŀäºĭ
    0.06
    ffective
    0.06
    ongan
    0.06
    esia
    0.06
    urgical
    0.06
    lean
    0.06
    ãĤĴãģĭãģijãģ¦
    0.05
    Ùĩاء
    0.05
    Activations Density 0.001%

    No Known Activations