© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18672
    Prev
    Next
    INDEX
    Explanations

    not, doesn't, cannot

    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
    raf
    -0.05
    noÅĽÄĩ
    -0.05
    erness
    -0.05
    ç»Ŀ
    -0.05
    úd
    -0.05
    اÙĨد
    -0.05
    .main
    -0.05
    æŃ£å½ĵ
    -0.05
     sen
    -0.05
    èī²
    -0.05
    POSITIVE LOGITS
     gezi
    0.06
    asis
    0.06
    ebbe
    0.06
    éķ¿å®ĺ
    0.06
     trots
    0.06
    åİķ
    0.06
    ahrungs
    0.06
     ké
    0.06
    anski
    0.06
    urgi
    0.06
    Activations Density 0.017%

    No Known Activations