© 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. 20870
    Prev
    Next
    INDEX
    Explanations

    user account management

    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
     باخت
    -0.06
     banca
    -0.06
    æĬķèµĦä¼ģä¸ļ
    -0.06
    ibar
    -0.05
    viso
    -0.05
    attle
    -0.05
    ç§ī
    -0.05
    é¢ĨåŁŁä¸Ń
    -0.05
    -dem
    -0.05
    izas
    -0.05
    POSITIVE LOGITS
    и
    0.06
    raise
    0.06
    enda
    0.05
    union
    0.05
    emin
    0.05
    éĹ¹
    0.05
    urat
    0.05
    åIJįåŃĹåı«
    0.05
    peon
    0.05
     Pearce
    0.05
    Activations Density 0.015%

    No Known Activations