© 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. 17858
    Prev
    Next
    INDEX
    Explanations

    number or age

    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
    å¾·æĸ¯
    -0.06
    ä¸ĭåIJĮ
    -0.06
    ambar
    -0.06
    è¿Ł
    -0.06
     Confeder
    -0.06
    fahren
    -0.06
    Apart
    -0.05
    ract
    -0.05
     substantially
    -0.05
    wy
    -0.05
    POSITIVE LOGITS
    ufs
    0.06
    yle
    0.06
    ifr
    0.05
    æ±Ģ
    0.05
     grain
    0.05
    qc
    0.05
     Sav
    0.05
     baked
    0.05
    çIJ³
    0.05
    æ¶ĤæĬ¹
    0.05
    Activations Density 0.023%

    No Known Activations