© 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. 17459
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    geführten
    -0.07
    volve
    -0.06
    ollar
    -0.06
    为éĿŀ
    -0.06
    kod
    -0.06
     znak
    -0.06
    zent
    -0.06
    walten
    -0.06
    erer
    -0.06
    eday
    -0.06
    POSITIVE LOGITS
    avor
    0.06
    1
    0.05
    ort
    0.05
    åĽŀäºĭ
    0.05
     None
    0.05
    2
    0.05
    åīįèĢħ
    0.05
    ul
    0.05
    end
    0.05
    ipher
    0.05
    Activations Density 0.096%

    No Known Activations