© 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. 22593
    Prev
    Next
    INDEX
    Explanations

    asking for or giving information

    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
    imax
    -0.06
    ÙĪا
    -0.06
    kün
    -0.06
    åı¯æ¢¦
    -0.06
    oad
    -0.06
    odox
    -0.06
    对å®ĥ
    -0.06
    olet
    -0.05
    ormais
    -0.05
    asma
    -0.05
    POSITIVE LOGITS
    诱
    0.06
    pll
    0.05
     Converts
    0.05
     Convert
    0.05
    çĭĤ
    0.05
     reason
    0.05
    ä¸ĢäºĮ
    0.05
    ÚĺÛĮ
    0.05
    Ptr
    0.05
    #plt
    0.05
    Activations Density 0.001%

    No Known Activations