© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18280
    Prev
    Next
    INDEX
    Explanations

    grammatical errors or typographical mistakes

    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
    oss
    -0.06
     sequences
    -0.06
     reconstruction
    -0.06
     sequence
    -0.06
     reconstruct
    -0.05
     structures
    -0.05
     structure
    -0.05
     sequencing
    -0.05
     Sequence
    -0.05
    çĽĶ
    -0.05
    POSITIVE LOGITS
    è¿Ļ对
    0.06
    çŁ¥å·±
    0.06
    idel
    0.06
    æĹłè¾¹
    0.06
    quÃŃ
    0.06
    éĤ
    0.06
    oho
    0.06
    inidad
    0.06
    ELLO
    0.06
    érc
    0.06
    Activations Density 0.003%

    No Known Activations