© 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. 20767
    Prev
    Next
    INDEX
    Explanations

    natural environment or resources

    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
    راج
    -0.07
    -
    -0.06
    æ°ijäºĭ
    -0.06
    -0.05
    (
    -0.05
    allis
    -0.05
    **
    -0.05
    `
    -0.05
    "
    -0.05
    sig
    -0.05
    POSITIVE LOGITS
    çŀĦ
    0.07
     Secretario
    0.07
     ÙħÙĪض
    0.06
    tory
    0.06
    "user
    0.06
     consecutivo
    0.06
    åħ¥éĩij
    0.06
    èĢĮåĸ»
    0.06
    زاÙĨ
    0.06
    irkan
    0.06
    Activations Density 0.001%

    No Known Activations