© 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. 20338
    Prev
    Next
    INDEX
    Explanations

    was installed formerly

    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
    under
    -0.06
     p
    -0.05
     tr
    -0.05
    nder
    -0.05
    erton
    -0.05
    æ°ijåĬŀ
    -0.05
     her
    -0.05
     under
    -0.05
    åijĪ
    -0.05
    æĮīåħ¶
    -0.05
    POSITIVE LOGITS
    _align
    0.07
    à¸ķรà¸ĩà¸ģัà¸ļ
    0.07
    .align
    0.07
    ievo
    0.06
    COMPARE
    0.06
    缴æݥ使çĶ¨
    0.06
    éľĦ
    0.06
     absorbing
    0.06
     nave
    0.06
    ůj
    0.06
    Activations Density 0.171%

    No Known Activations