© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16646
    Prev
    Next
    INDEX
    Explanations

    political censorship and bias

    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
    Negative Logits
    第äºĮ大
    -0.07
    å¾·éŁ³
    -0.07
    yses
    -0.06
    missão
    -0.06
    piring
    -0.06
    larg
    -0.06
    isiin
    -0.06
    менÑıÑĤÑĮ
    -0.06
    è¦ģ大
    -0.06
    ünchen
    -0.06
    POSITIVE LOGITS
    代
    0.06
    alic
    0.05
     ends
    0.05
    çģŃ
    0.05
    olis
    0.05
    âĢ¦
    0.05
    天é¾Ļ
    0.05
     fluids
    0.05
    ä»»
    0.05
    isan
    0.05
    Activations Density 0.011%

    No Known Activations