© 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. 21315
    Prev
    Next
    INDEX
    Explanations

    **START OF SENTENCE/PHRASE**

    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
     séqu
    -0.07
    IPP
    -0.06
    paque
    -0.05
    ä¸Ńåħ¬
    -0.05
    èº
    -0.05
     dihad
    -0.05
    unj
    -0.05
    Isn
    -0.05
    -inner
    -0.05
    ipas
    -0.05
    POSITIVE LOGITS
    Ñģловно
    0.06
     **.**
    0.06
    对çĻ½
    0.06
    缮ä¸į
    0.05
    å®ŀåľ¨å¤ª
    0.05
    wach
    0.05
    ÑĨÑİ
    0.05
    éĤĢ
    0.05
    人已
    0.05
    each
    0.05
    Activations Density 0.095%

    No Known Activations