© 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. 16846
    Prev
    Next
    INDEX
    Explanations

    mimic natural

    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
     Brandenburg
    -0.07
    ype
    -0.06
    agr
    -0.06
    åĨ³
    -0.05
    masked
    -0.05
    å®ļåŀĭ
    -0.05
    cego
    -0.05
    okia
    -0.05
     Bandara
    -0.05
    rome
    -0.05
    POSITIVE LOGITS
    æĬµæĬĹ
    0.06
     resistance
    0.06
    uiten
    0.06
    Resistance
    0.06
     Resistance
    0.06
    æ¯ı
    0.05
    以太
    0.05
    产åĵģåIJį称
    0.05
     Nature
    0.05
    èĩªçĦ¶èĢĮ
    0.05
    Activations Density 0.007%

    No Known Activations