© 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. 21696
    Prev
    Next
    INDEX
    Explanations

    increment progression

    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
    表示
    -0.06
    reo
    -0.06
     reap
    -0.06
     Feliz
    -0.06
    erti
    -0.06
     interrogation
    -0.05
    代
    -0.05
    åıįè¦Ĩ
    -0.05
     Crypt
    -0.05
    ä¸įçŁ¥éģĵ该
    -0.05
    POSITIVE LOGITS
    éĢĴå¢ŀ
    0.08
     incremental
    0.08
     progression
    0.07
    èİĺ
    0.06
     progressive
    0.06
     Progressive
    0.06
     progressively
    0.06
    increment
    0.06
     increment
    0.06
    å¢ŀéĩı
    0.06
    Activations Density 0.012%

    No Known Activations