© 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. 20342
    Prev
    Next
    INDEX
    Explanations

    advantages, gift, low incidence

    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
    thesize
    -0.06
    èĢĮ使
    -0.06
    éĹº
    -0.05
    wander
    -0.05
    esis
    -0.05
    micas
    -0.05
    favor
    -0.05
     cục
    -0.05
     تعب
    -0.05
    Localized
    -0.05
    POSITIVE LOGITS
    ampa
    0.06
     Sc
    0.06
    isc
    0.06
    ست
    0.06
    amar
    0.06
    idd
    0.06
    å®Įåħ¨
    0.05
     nemmeno
    0.05
    ç»Ŀ对
    0.05
    oret
    0.05
    Activations Density 0.008%

    No Known Activations