© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19285
    Prev
    Next
    INDEX
    Explanations

    start or begin

    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
    ÑģÑĮ
    -0.07
    persona
    -0.07
    iente
    -0.06
    说好
    -0.06
    ver
    -0.06
    erc
    -0.06
     semula
    -0.06
    harma
    -0.06
    Ģ
    -0.06
    Ñĥже
    -0.06
    POSITIVE LOGITS
    qus
    0.06
    ioned
    0.06
    å¾Ĺå½ĵ
    0.06
    bonne
    0.05
    ogat
    0.05
    inee
    0.05
    åijĨ
    0.05
     bree
    0.05
    æıIJåıĬ
    0.05
    强çĥĪçļĦ
    0.05
    Activations Density 0.009%

    No Known Activations