© 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. 17987
    Prev
    Next
    INDEX
    Explanations

    numbers following "uen"

    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
    ably
    -0.06
    äºĮéĥİ
    -0.06
    *size
    -0.06
    áĥ§
    -0.06
     vs
    -0.06
     All
    -0.05
    ners
    -0.05
    äºĶæĮĩ
    -0.05
    ively
    -0.05
     likely
    -0.05
    POSITIVE LOGITS
     Apel
    0.05
    çº
    0.05
    åİŁæ±ģ
    0.05
     immortal
    0.05
    zap
    0.05
    anker
    0.05
    å¤ļå¤ļ
    0.05
    pras
    0.05
    apper
    0.05
    letal
    0.05
    Activations Density 0.002%

    No Known Activations