© 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. 17105
    Prev
    Next
    INDEX
    Explanations

    organic electro-optic materials

    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
    abo
    -0.06
     bore
    -0.06
     ref
    -0.05
    uns
    -0.05
    æŀĦéĢł
    -0.05
    ضاÙĨ
    -0.05
    åħīäºĨ
    -0.05
     mineral
    -0.05
    si
    -0.05
    åĪļ
    -0.05
    POSITIVE LOGITS
    鸦
    0.07
    ieder
    0.06
    iens
    0.06
    纶
    0.06
    (.
    0.06
     princ
    0.06
    éĻįåİĭ
    0.06
    edar
    0.06
    anej
    0.05
     publique
    0.05
    Activations Density 0.053%

    No Known Activations