© 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. 18602
    Prev
    Next
    INDEX
    Explanations

    date and number

    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
    ermann
    -0.06
    uiten
    -0.06
    lust
    -0.06
    ombs
    -0.06
    uce
    -0.06
    Parte
    -0.06
     Ùħزد
    -0.06
    æĸ°æĶ¿
    -0.06
    liegen
    -0.06
    urope
    -0.06
    POSITIVE LOGITS
     differs
    0.05
    åıijå±ķ模å¼ı
    0.05
     شب
    0.05
    adis
    0.05
    Prob
    0.05
     probabilities
    0.05
    ille
    0.05
    Spec
    0.05
    General
    0.05
    Rem
    0.05
    Activations Density 0.002%

    No Known Activations