© 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. 20277
    Prev
    Next
    INDEX
    Explanations

    website links and documentation

    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
    ider
    -0.05
    еÑħ
    -0.05
    -,
    -0.05
    vore
    -0.05
    chner
    -0.05
    fw
    -0.05
    -liter
    -0.05
    ÑĢик
    -0.05
     Exped
    -0.05
     high
    -0.05
    POSITIVE LOGITS
    vind
    0.06
    éł
    0.06
    à¹ģà¸Ĺà¹ī
    0.06
    æľīçļĦæĺ¯
    0.06
    æī¾ä¸įåĪ°
    0.06
    ัà¸ķ
    0.06
    apura
    0.06
    urada
    0.06
    laub
    0.06
    æŃ£ä¸Ń
    0.05
    Activations Density 0.008%

    No Known Activations