© 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. 16989
    Prev
    Next
    INDEX
    Explanations

    powers and exponents

    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
    åĪĨéħįçļĦ
    -0.05
    éŀį
    -0.05
    lob
    -0.05
    æī¿
    -0.05
    éħį
    -0.05
    iy
    -0.05
    åĪĨéħį
    -0.05
    iar
    -0.05
    etheless
    -0.05
    ke
    -0.05
    POSITIVE LOGITS
    ãĤ²ãĥ³
    0.07
    amay
    0.07
    abaj
    0.06
    agama
    0.06
    åı£ãģ«
    0.06
    edal
    0.06
    ημα
    0.06
    ëŀij
    0.06
     fod
    0.06
    ä¸įåģľçļĦ
    0.06
    Activations Density 0.020%

    No Known Activations