© 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. 18713
    Prev
    Next
    INDEX
    Explanations

    scattering and its effects

    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
    akhir
    -0.07
    没å¤ļä¹ħ
    -0.06
    etrieben
    -0.06
    aim
    -0.06
    auan
    -0.06
    лежа
    -0.06
    ležité
    -0.06
    ysl
    -0.06
    ì²ĺ
    -0.06
     Isles
    -0.05
    POSITIVE LOGITS
    ingly
    0.08
    ä¸ŃåĽ½å®¶
    0.06
    讨
    0.06
    ording
    0.06
     crush
    0.05
    paket
    0.05
    ì¦Ŀ
    0.05
    champ
    0.05
    è¨İ
    0.05
    çķ¸
    0.05
    Activations Density 0.001%

    No Known Activations