© 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. 17193
    Prev
    Next
    INDEX
    Explanations

    franchise titles

    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
    ality
    -0.06
    ärt
    -0.06
    bili
    -0.06
    éĤ£åº§
    -0.06
    å°±æĺ¯ä»ĸ
    -0.06
    oseb
    -0.06
    å¾ģ稿
    -0.06
    built
    -0.06
    erno
    -0.06
     Notre
    -0.06
    POSITIVE LOGITS
    å¹»
    0.05
    spiracy
    0.05
    สาย
    0.05
    åĨ³å®ļ
    0.05
     plenty
    0.05
     sust
    0.05
    Desc
    0.05
    æĺıè¿·
    0.05
    lij
    0.05
    shaw
    0.05
    Activations Density 0.002%

    No Known Activations