© 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. 17232
    Prev
    Next
    INDEX
    Explanations

    quantitative or list data

    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
    enges
    -0.07
     Jat
    -0.06
    Qualifier
    -0.06
     Leng
    -0.06
    confidence
    -0.06
    etta
    -0.06
     descriptors
    -0.06
    pekt
    -0.06
    etag
    -0.06
     geometr
    -0.06
    POSITIVE LOGITS
    zul
    0.06
     ØŃص
    0.06
     d
    0.05
     sod
    0.05
    è¿Ļéĥ¨åĪĨ
    0.05
     purely
    0.05
    æ°´å¹³
    0.05
    裸
    0.05
    мÑı
    0.05
    综åIJĪè¿IJçĶ¨
    0.05
    Activations Density 0.150%

    No Known Activations