© 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. 20526
    Prev
    Next
    INDEX
    Explanations

    Congratulations and welcome

    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
    θη
    -0.06
    ÏĨη
    -0.06
    mobil
    -0.06
    onat
    -0.06
    onse
    -0.06
    oje
    -0.06
    ê°ģ
    -0.06
     erotisch
    -0.06
     encaps
    -0.06
    antik
    -0.06
    POSITIVE LOGITS
    士
    0.06
    åħ¶èĩªçĦ¶
    0.05
     vested
    0.05
    è®Ń
    0.05
     plainly
    0.05
    èĪ
    0.05
     pent
    0.05
    à¥įह
    0.05
     +/-
    0.05
     &
    0.05
    Activations Density 0.010%

    No Known Activations