© 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. 19790
    Prev
    Next
    INDEX
    Explanations

    a followed by a noun

    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
    ism
    -0.07
    ile
    -0.05
     theirs
    -0.05
    w
    -0.05
    çµĤ
    -0.05
    à¤Ĭ
    -0.05
    å±ķ
    -0.05
    inum
    -0.05
    he
    -0.05
    ouch
    -0.05
    POSITIVE LOGITS
    ,eg
    0.07
    æĭĮåĮĢ
    0.06
    rek
    0.06
    atteri
    0.06
    resto
    0.06
     shl
    0.06
    cte
    0.06
     intl
    0.06
     envies
    0.06
    anha
    0.06
    Activations Density 0.015%

    No Known Activations