© 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. 17651
    Prev
    Next
    INDEX
    Explanations

    `../../../stylesheet.css`

    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
    èĪ
    -0.06
    cont
    -0.06
    æŃ¤èµ·
    -0.05
    beck
    -0.05
    åıĮéļıæľº
    -0.05
    TS
    -0.05
    rix
    -0.05
    ç»ıæµİåĴĮ
    -0.05
    rais
    -0.05
    elte
    -0.05
    POSITIVE LOGITS
    çĿģ
    0.06
    atr
    0.06
     nô
    0.06
    å¤ļæķ°
    0.06
    à¸Ļà¸Ļ
    0.06
    åį·è½´
    0.06
    åħ¨åijĺ
    0.06
     ampli
    0.06
    chage
    0.05
    gu
    0.05
    Activations Density 0.001%

    No Known Activations