© 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. 20368
    Prev
    Next
    INDEX
    Explanations

    9/11 attacks World Trade Center

    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
    acin
    -0.07
     rocker
    -0.05
    landers
    -0.05
     Õº
    -0.05
    åıªæīĭ
    -0.05
    为éļ¾
    -0.05
    ç¡Ŀéħ¸çĽIJ
    -0.05
     Eins
    -0.05
     biv
    -0.05
    alti
    -0.05
    POSITIVE LOGITS
    polis
    0.06
     Vulner
    0.06
    лай
    0.05
    ืà¹Īà¸Ńà¸Ķ
    0.05
    èĢĺ
    0.05
    è®°å½ķ
    0.05
    åĴĮé»Ħ
    0.05
    ADED
    0.05
     vulnerabilities
    0.05
     Trusted
    0.05
    Activations Density 0.008%

    No Known Activations