© 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. 19148
    Prev
    Next
    INDEX
    Explanations

    indefinite article preceding noun

    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
    Âł
    -0.05
    ech
    -0.05
     nowhere
    -0.05
     options
    -0.05
     opportunities
    -0.05
    å¤ļçļĦ
    -0.05
    éĶĻ
    -0.05
     relative
    -0.05
    erable
    -0.05
    temp
    -0.05
    POSITIVE LOGITS
    éĺ³å¸Ĥ
    0.07
     cursus
    0.06
    ä¸Ģ缴ä¿ĿæĮģ
    0.06
    ivec
    0.06
    hait
    0.06
    iant
    0.06
    rex
    0.06
    å¨ģ
    0.06
    inhas
    0.06
     atra
    0.06
    Activations Density 0.001%

    No Known Activations