© 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. 21335
    Prev
    Next
    INDEX
    Explanations

    I was

    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
    -0.07
    olt
    -0.05
     verses
    -0.05
     tid
    -0.05
    zew
    -0.05
    åIJĪ
    -0.05
     features
    -0.05
    gin
    -0.05
    fib
    -0.05
    iver
    -0.04
    POSITIVE LOGITS
    kamp
    0.07
    -Nov
    0.06
    ,content
    0.06
     ê±°ëĵŃ
    0.06
    ạp
    0.06
    วัà¸Ĵà¸Ļà¹Į
    0.06
    éĹ®åıĬ
    0.06
    è¾Ī
    0.06
    yek
    0.06
    unce
    0.06
    Activations Density 0.079%

    No Known Activations