© 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. 21443
    Prev
    Next
    INDEX
    Explanations

    civil war

    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
     fort
    -0.06
     re
    -0.06
    gal
    -0.05
     open
    -0.05
    绣
    -0.05
    éľĢè¦ģ
    -0.05
    un
    -0.05
    解éĻ¤
    -0.05
     "
    -0.05
    awa
    -0.05
    POSITIVE LOGITS
    ppo
    0.07
    deles
    0.07
    åı±
    0.07
    åĪĨãģĭãĤĬ
    0.07
    人æ°ijåħ±åĴĮåĽ½
    0.06
     Dud
    0.06
    éĤ£ä»½
    0.06
    hes
    0.06
    ãĤıãģĭãĤĬ
    0.06
     Insider
    0.06
    Activations Density 0.140%

    No Known Activations