© 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. 19086
    Prev
    Next
    INDEX
    Explanations

    parents' experiences

    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
    dir
    -0.05
     buna
    -0.05
     vers
    -0.05
    çģĮ
    -0.05
    ole
    -0.05
    æµģåĬ¨
    -0.05
    ol
    -0.04
    ir
    -0.04
     Vie
    -0.04
    ache
    -0.04
    POSITIVE LOGITS
    lettere
    0.07
     Orr
    0.07
    istin
    0.06
    toj
    0.06
    rahat
    0.06
    HAV
    0.06
    atr
    0.06
    stil
    0.06
    oppel
    0.06
    Äĥt
    0.06
    Activations Density 0.034%

    No Known Activations