© 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. 22048
    Prev
    Next
    INDEX
    Explanations

    long-term trends

    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
    wic
    -0.06
     Wax
    -0.06
    bite
    -0.06
    èĢĮçŁ¥
    -0.06
    azah
    -0.06
    é«ĺ级
    -0.06
     Exhaust
    -0.06
     spent
    -0.05
    lite
    -0.05
    ä¸½å¨ľ
    -0.05
    POSITIVE LOGITS
    çĨ
    0.06
    è¿ľå¤ĦçļĦ
    0.06
    anc
    0.06
    è¿ľå¤Ħ
    0.05
    å¿ĺ
    0.05
    astro
    0.05
     Lever
    0.05
     Terb
    0.05
     mÃŃn
    0.05
    éģĵ
    0.05
    Activations Density 0.006%

    No Known Activations