© 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. 18198
    Prev
    Next
    INDEX
    Explanations

    while (true)

    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
     otherwise
    -0.07
    otherwise
    -0.07
    ooth
    -0.06
    ewhat
    -0.06
    è¿Ľè¡Įæµĭè¯ķ
    -0.06
    设为
    -0.06
    é¸
    -0.06
    fund
    -0.06
    abor
    -0.06
     elsewhere
    -0.05
    POSITIVE LOGITS
     sẵn
    0.06
    ugel
    0.06
    ydi
    0.06
    å®ĥå°Ĩ
    0.06
    ting
    0.05
    æķ£
    0.05
    áž
    0.05
    ÑģÑĤнаÑı
    0.05
    åİŁä»¶åıĬ
    0.05
     mains
    0.05
    Activations Density 0.001%

    No Known Activations