© 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. 19239
    Prev
    Next
    INDEX
    Explanations

    transition from or to

    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
    -thirds
    -0.07
    宿
    -0.06
    bod
    -0.06
     gom
    -0.06
    ÙĬÙĭا
    -0.06
    pisode
    -0.06
    Ø©
    -0.05
    eted
    -0.05
    деÑģÑıÑĤ
    -0.05
    RIGHT
    -0.05
    POSITIVE LOGITS
    íķľ
    0.06
    antas
    0.06
    ser
    0.06
    antly
    0.06
    ê¸Ī
    0.06
    uszcz
    0.06
    åĨ·èIJ½
    0.06
    ä½ķ为
    0.06
    ured
    0.06
     Transition
    0.06
    Activations Density 0.012%

    No Known Activations