© 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. 21320
    Prev
    Next
    INDEX
    Explanations

    PWN, building plans

    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
     inhabit
    -0.05
    chutz
    -0.05
     short
    -0.05
    ↵
    -0.05
    ذار
    -0.05
    dr
    -0.05
     Short
    -0.05
     dr
    -0.04
    oji
    -0.04
    short
    -0.04
    POSITIVE LOGITS
    çī¹åĭĴ
    0.06
    èn
    0.06
    asilan
    0.06
    ç»ŀ
    0.06
     nhau
    0.06
     chó
    0.06
     entière
    0.06
    çĿ¹
    0.06
    rid
    0.05
    ASY
    0.05
    Activations Density 0.001%

    No Known Activations