© 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. 17688
    Prev
    Next
    INDEX
    Explanations

    **waterways and adjacent locations**

    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
    upa
    -0.05
     Prepar
    -0.05
     flowing
    -0.05
    äºĶ级
    -0.05
     Atkins
    -0.05
    å¥Ķèħ¾
    -0.05
    æ¶īæ°´
    -0.05
    ë©ľ
    -0.05
    antin
    -0.05
    ri
    -0.04
    POSITIVE LOGITS
    amic
    0.07
    ernes
    0.06
    ves
    0.06
    ä¸Ģæŀ¶
    0.06
    icket
    0.06
    æĭ¯æķij
    0.06
    ä¸ĩæĪ·
    0.06
    ุà¹Īà¸Ļ
    0.06
    ä¸į失
    0.06
    roid
    0.06
    Activations Density 0.008%

    No Known Activations