© 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. 20610
    Prev
    Next
    INDEX
    Explanations

    technical terms and 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
    egiatan
    -0.08
    JD
    -0.06
    orre
    -0.06
    spel
    -0.06
    anu
    -0.06
    amor
    -0.06
    客
    -0.05
    okus
    -0.05
    гада
    -0.05
     sabemos
    -0.05
    POSITIVE LOGITS
    они
    0.05
    ham
    0.05
    alti
    0.05
    await
    0.05
    efore
    0.05
    phony
    0.05
    ungen
    0.05
    iless
    0.05
    ÙĬÙģ
    0.05
     respective
    0.05
    Activations Density 0.007%

    No Known Activations