© 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. 16926
    Prev
    Next
    INDEX
    Explanations

    com.jd

    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
    ould
    -0.06
    aros
    -0.06
    еÑīа
    -0.06
    /DD
    -0.06
    @$
    -0.06
    å°ıåĮºåĨħ
    -0.06
    ÑĤаÑĤа
    -0.06
    ä¸īæĿ¿
    -0.06
    åĴĮ第
    -0.06
    azzur
    -0.06
    POSITIVE LOGITS
    oret
    0.06
    èĩªå·±
    0.05
    -
    0.05
    etheless
    0.05
     comport
    0.05
    ogonal
    0.05
    ier
    0.05
    à¹Ģร
    0.05
    avier
    0.05
     incumb
    0.05
    Activations Density 0.022%

    No Known Activations