© 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. 17714
    Prev
    Next
    INDEX
    Explanations

    Systems and Services Ltd Company

    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
    对å¾ħ
    -0.06
     Larson
    -0.06
    Dict
    -0.06
    infeld
    -0.06
    apur
    -0.06
    fone
    -0.06
    lebn
    -0.06
    åĬį
    -0.06
    tement
    -0.06
    bart
    -0.06
    POSITIVE LOGITS
    razy
    0.05
    åħĪ
    0.05
     ambi
    0.05
    çIJħ
    0.05
    seb
    0.05
    åħĪåľ¨
    0.05
     ór
    0.05
     metabol
    0.05
    段
    0.04
    åĢĴ
    0.04
    Activations Density 0.028%

    No Known Activations