© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19595
    Prev
    Next
    INDEX
    Explanations

    useState and .observable variable declarations

    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
    isle
    -0.05
    ys
    -0.05
    åĹ£
    -0.05
     obstant
    -0.05
    ί
    -0.05
    itung
    -0.05
    otos
    -0.05
    اص
    -0.05
    osoph
    -0.05
    it
    -0.05
    POSITIVE LOGITS
    quete
    0.06
    åİŁä»¶åıĬ
    0.06
    pired
    0.06
    ampler
    0.06
    curring
    0.06
     Dread
    0.06
    à¹Ģà¸Ķียว
    0.06
    geben
    0.06
    ünchen
    0.06
    á»ħn
    0.06
    Activations Density 0.001%

    No Known Activations