© 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. 17534
    Prev
    Next
    INDEX
    Explanations

    optional

    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
    opportun
    -0.06
    itação
    -0.06
     опеÑĢаÑĤ
    -0.06
    دÙĬر
    -0.06
    agem
    -0.06
     Deixe
    -0.06
    ÑģÑĤеÑĢа
    -0.06
    dea
    -0.05
    èĩªå·±çļĦæĥ³æ³ķ
    -0.05
    ÑĩаÑģÑĤли
    -0.05
    POSITIVE LOGITS
    VAL
    0.06
     inf
    0.06
     tú
    0.06
    ifel
    0.06
    å°±åĪ°äºĨ
    0.06
    ä¼ļ说
    0.06
    ä¸įèĥľæķ°
    0.06
    çĤİçļĦ
    0.05
    æĸ°åħµ
    0.05
    tt
    0.05
    Activations Density 0.004%

    No Known Activations