© 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. 18946
    Prev
    Next
    INDEX
    Explanations

    Unless required by law

    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
     
    -0.07
     ($)
    -0.06
    nado
    -0.06
    genomen
    -0.06
     Servi
    -0.06
    bahn
    -0.06
    è¸Ĭè·ĥ
    -0.06
    EMPL
    -0.06
    ISTER
    -0.06
    ploy
    -0.06
    POSITIVE LOGITS
    ä¿ĥ
    0.06
     g
    0.05
     with
    0.05
     B
    0.05
    éĢŁ
    0.05
     rum
    0.05
    容
    0.05
     pen
    0.05
    "...
    0.05
     am
    0.05
    Activations Density 0.003%

    No Known Activations