© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18975
    Prev
    Next
    INDEX
    Explanations

    settlement names

    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
    aven
    -0.06
    æīĭä¸Ń
    -0.05
     stor
    -0.05
    &A
    -0.05
    ä¸įè¨Ģ
    -0.05
    Vu
    -0.05
    scr
    -0.05
     rare
    -0.05
     neutral
    -0.05
    alking
    -0.05
    POSITIVE LOGITS
    æĺ¯éĿł
    0.07
    anlı
    0.06
    éĿłå±±
    0.06
    аниз
    0.06
    éĿłèijĹ
    0.06
    ziem
    0.06
     neoliber
    0.06
    å½ĵå±Ģ
    0.06
    æĪijåij¢
    0.06
    æĸ°ç¤¾
    0.06
    Activations Density 0.023%

    No Known Activations