© 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. 21848
    Prev
    Next
    INDEX
    Explanations

    evaluation of

    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
    èĴĻ
    -0.05
     specimen
    -0.05
    reto
    -0.05
     into
    -0.05
    ja
    -0.05
     engagement
    -0.05
    za
    -0.04
    ×ŀש
    -0.04
    ko
    -0.04
    ino
    -0.04
    POSITIVE LOGITS
    ovol
    0.07
    ecca
    0.07
    adie
    0.07
    alat
    0.06
    rufen
    0.06
    ืà¹īà¸Ļ
    0.06
    LLU
    0.06
    agrid
    0.06
    antin
    0.06
    eite
    0.06
    Activations Density 0.092%

    No Known Activations