© 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. 22265
    Prev
    Next
    INDEX
    Explanations

    catching up, figure out, reinvent the wheel

    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
    -0.06
     Tel
    -0.05
    èµĦ
    -0.05
    ↵↵
    -0.05
    ue
    -0.04
     II
    -0.04
    elah
    -0.04
     ——
    -0.04
    el
    -0.04
    æĸ¯
    -0.04
    POSITIVE LOGITS
    voz
    0.07
    åĩºä¸į
    0.07
    thon
    0.07
    baar
    0.07
    ioso
    0.07
    uario
    0.07
    èĩ
    0.07
    å½Ĵå±ŀäºİä¸Ĭå¸Ĥåħ¬åı¸
    0.07
    anze
    0.07
     concurr
    0.07
    Activations Density 0.005%

    No Known Activations