© 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. 20634
    Prev
    Next
    INDEX
    Explanations

    Cholesky decomposition

    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
    anders
    -0.06
    ajn
    -0.06
     Sense
    -0.05
    ieg
    -0.05
    rever
    -0.05
    _WRONG
    -0.05
    éĢłçī©
    -0.05
     repe
    -0.05
    Sense
    -0.05
    arging
    -0.05
    POSITIVE LOGITS
    éħ¸çĶľ
    0.07
     artifici
    0.06
    лко
    0.06
    men
    0.05
    å¸ľ
    0.05
     اÙģت
    0.05
    Interpreter
    0.05
    颤
    0.05
    ä¸įæĭĶ
    0.05
    大åĪĢ
    0.05
    Activations Density 0.024%

    No Known Activations