© 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. 17910
    Prev
    Next
    INDEX
    Explanations

    storage units (GB, MB)

    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
    adar
    -0.06
     اÙĦأعÙĦÙī
    -0.06
    itra
    -0.06
    iltr
    -0.06
    hin
    -0.06
    Lint
    -0.06
    iday
    -0.06
    波波
    -0.06
    à¹Ħหรà¹Ī
    -0.06
    Technologie
    -0.06
    POSITIVE LOGITS
    fulness
    0.05
    াà¦ķ
    0.05
    etano
    0.05
    çĶŁäºİ
    0.05
    æľīæľºä¼ļ
    0.05
     Äijáo
    0.05
    ä¸Ĭä¸ĭ
    0.05
    umar
    0.05
    å¸ĿçļĦ
    0.05
    ä¹ĭéĹ´åŃĺåľ¨
    0.05
    Activations Density 0.004%

    No Known Activations